deepgeek/gradio-webrtc
2
0
Fork 0
mirror of https://github.com/HumanAIGC-Engineering/gradio-webrtc.git synced 2026-02-05 18:09:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

Rebrand to FastRTC (#60)

Browse Source 
* Add code

* add code

* add code

* Rename messages

* rename

* add code

* Add demo

* docs + demos + bug fixes

* add code

* styles

* user guide

* Styles

* Add code

* misc docs updates

* print nit

* whisper + pr

* url for images

* whsiper update

* Fix bugs

* remove demo files

* version number

* Fix pypi readme

* Fix

* demos

* Add llama code editor

* Update llama code editor and object detection cookbook

* Add more cookbook demos

* add code

* Fix links for PR deploys

* add code

* Fix the install

* add tts

* TTS docs

* Typo

* Pending bubbles for reply on pause

* Stream redesign (#63)

* better error handling

* Websocket error handling

* add code

---------

Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local>

* remove docs from dist

* Some docs typos

* more typos

* upload changes + docs

* docs

* better phone

* update docs

* add code

* Make demos better

* fix docs + websocket start_up

* remove mention of FastAPI app

* fastphone tweaks

* add code

* ReplyOnStopWord fixes

* Fix cookbook

* Fix pypi readme

* add code

* bump versions

* sambanova cookbook

* Fix tags

* Llm voice chat

* kyutai tag

* Add error message to all index.html

* STT module uses Moonshine

* Not required from typing extensions

* fix llm voice chat

* Add vpn warning

* demo fixes

* demos

* Add more ui args and gemini audio-video

* update cookbook

* version 9

---------

Co-authored-by: Freddy Boulton <freddyboulton@hf-freddy.local>
This commit is contained in:
Freddy Boulton
2025-02-24 01:13:42 -05:00
committed by GitHub
parent 36190066ec
commit 853d6a06b5
131 changed files with 12349 additions and 4741 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
demo/README.md
View File

@@ -1,44 +0,0 @@
---
license: mit
tags:
- object-detection
- computer-vision
- yolov10
datasets:
- detection-datasets/coco
sdk: gradio
sdk_version: 5.0.0b1
---
### Model Description
[YOLOv10: Real-Time End-to-End Object Detection](https://arxiv.org/abs/2405.14458v1)
- arXiv: https://arxiv.org/abs/2405.14458v1
- github: https://github.com/THU-MIG/yolov10
### Installation
```
pip install supervision git+https://github.com/THU-MIG/yolov10.git
```
### Yolov10 Inference
```python
from ultralytics import YOLOv10
import supervision as sv
import cv2
IMAGE_PATH = 'dog.jpeg'
model = YOLOv10.from_pretrained('jameslahm/yolov10{n/s/m/b/l/x}')
model.predict(IMAGE_PATH, show=True)
```
### BibTeX Entry and Citation Info
```
@article{wang2024yolov10,
title={YOLOv10: Real-Time End-to-End Object Detection},
author={Wang, Ao and Chen, Hui and Liu, Lihao and Chen, Kai and Lin, Zijia and Han, Jungong and Ding, Guiguang},
journal={arXiv preprint arXiv:2405.14458},
year={2024}
}
```

105
demo/also_return_text.py
View File

@@ -1,105 +0,0 @@
import logging
import os
import gradio as gr
import numpy as np
from gradio_webrtc import AdditionalOutputs, WebRTC
from pydub import AudioSegment
from twilio.rest import Client
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.FileHandler("gradio_webrtc.log")
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("gradio_webrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(num_steps):
for i in range(num_steps):
segment = AudioSegment.from_file(
"/Users/freddy/sources/gradio/demo/scratch/audio-streaming/librispeech.mp3"
)
yield (
(
segment.frame_rate,
np.array(segment.get_array_of_samples()).reshape(1, -1),
),
AdditionalOutputs(
f"Hello, from step {i}!",
"/Users/freddy/sources/gradio/demo/scratch/audio-streaming/librispeech.mp3",
),
)
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Audio Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
audio = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="audio",
)
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
textbox = gr.Textbox(placeholder="Output will appear here.")
audio_file = gr.Audio()
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio], trigger=button.click
)
audio.on_additional_outputs(
fn=lambda t, a: (f"State changed to {t}.", a),
outputs=[textbox, audio_file],
)
if __name__ == "__main__":
demo.launch(
allowed_paths=[
"/Users/freddy/sources/gradio/demo/scratch/audio-streaming/librispeech.mp3"
]
)

367
demo/app.py
View File

@@ -1,367 +0,0 @@
import os
import gradio as gr
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "The height of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"width": {
"type": "int | str | None",
"default": "None",
"description": "The width of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"label": {
"type": "str | None",
"default": "None",
"description": "the label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.",
},
"min_width": {
"type": "int",
"default": "160",
"description": "minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.",
},
"interactive": {
"type": "bool | None",
"default": "None",
"description": "if True, will allow users to upload a video; if False, can only be used to display videos. If not provided, this is inferred based on whether the component is used as an input or output.",
},
"visible": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "an optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"elem_classes": {
"type": "list[str] | str | None",
"default": "None",
"description": "an optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"render": {
"type": "bool",
"default": "True",
"description": "if False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.",
},
"key": {
"type": "int | str | None",
"default": "None",
"description": "if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.",
},
"mirror_webcam": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}
abs_path = os.path.join(os.path.dirname(__file__), "css.css")
with gr.Blocks(
css_paths=abs_path,
theme=gr.themes.Default(
font_mono=[
gr.themes.GoogleFont("Inconsolata"),
"monospace",
],
),
) as demo:
gr.Markdown(
"""
<h1 style='text-align: center; margin-bottom: 1rem'> Gradio WebRTC ⚡️ </h1>
<div style="display: flex; flex-direction: row; justify-content: center">
<img style="display: block; padding-right: 5px; height: 20px;" alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.6%20-%20orange">
<a href="https://github.com/freddyaboulton/gradio-webrtc" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/github-white?logo=github&logoColor=black"></a>
</div>
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
## Installation
```bash
pip install gradio_webrtc
```
## Examples:
1. [Object Detection from Webcam with YOLOv10](https://huggingface.co/spaces/freddyaboulton/webrtc-yolov10n) 📷
2. [Streaming Object Detection from Video with RT-DETR](https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc) 🎥
3. [Text-to-Speech](https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc) 🗣️
4. [Conversational AI](https://huggingface.co/spaces/freddyaboulton/omni-mini-webrtc) 🤖🗣️
## Usage
The WebRTC component supports the following three use cases:
1. [Streaming video from the user webcam to the server and back](#h-streaming-video-from-the-user-webcam-to-the-server-and-back)
2. [Streaming Video from the server to the client](#h-streaming-video-from-the-server-to-the-client)
3. [Streaming Audio from the server to the client](#h-streaming-audio-from-the-server-to-the-client)
4. [Streaming Audio from the client to the server and back (conversational AI)](#h-conversational-ai)
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
def detection(image, conf_threshold=0.3):
... your detection code here ...
with gr.Blocks() as demo:
image = WebRTC(label="Stream", mode="send-receive", modality="video")
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection,
inputs=[image, conf_threshold],
outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()
```
* Set the `mode` parameter to `send-receive` and `modality` to "video".
* The `stream` event's `fn` parameter is a function that receives the next frame from the webcam
as a **numpy array** and returns the processed frame also as a **numpy array**.
* Numpy arrays are in (height, width, 3) format where the color channels are in RGB format.
* The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component.
* The `time_limit` parameter is the maximum time in seconds the video stream will run. If the time limit is reached, the video stream will stop.
## Streaming Video from the server to the client
```python
import gradio as gr
from gradio_webrtc import WebRTC
import cv2
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
output_video = WebRTC(label="Video Stream", mode="receive", modality="video")
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video],
trigger=button.click
)
if __name__ == "__main__":
demo.launch()
```
* Set the "mode" parameter to "receive" and "modality" to "video".
* The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**.
* The only output allowed is the WebRTC component.
* The `trigger` parameter the gradio event that will trigger the webrtc connection. In this case, the button click event.
## Streaming Audio from the Server to the Client
```python
import gradio as gr
from pydub import AudioSegment
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file("/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav")
yield (segment.frame_rate, np.array(segment.get_array_of_samples()).reshape(1, -1))
with gr.Blocks() as demo:
audio = WebRTC(label="Stream", mode="receive", modality="audio")
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio],
trigger=button.click
)
```
* Set the "mode" parameter to "receive" and "modality" to "audio".
* The `stream` event's `fn` parameter is a generator function that yields the next audio segment as a tuple of (frame_rate, audio_samples).
* The numpy array should be of shape (1, num_samples).
* The `outputs` parameter should be a list with the WebRTC component as the only element.
## Conversational AI
```python
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC, StreamHandler
from queue import Queue
import time
class EchoHandler(StreamHandler):
def __init__(self) -> None:
super().__init__()
self.queue = Queue()
def receive(self, frame: tuple[int, np.ndarray] | np.ndarray) -> None:
self.queue.put(frame)
def emit(self) -> None:
return self.queue.get()
with gr.Blocks() as demo:
with gr.Column():
with gr.Group():
audio = WebRTC(
label="Stream",
rtc_configuration=None,
mode="send-receive",
modality="audio",
)
audio.stream(fn=EchoHandler(), inputs=[audio], outputs=[audio], time_limit=15)
if __name__ == "__main__":
demo.launch()
```
* Instead of passing a function to the `stream` event's `fn` parameter, pass a `StreamHandler` implementation. The `StreamHandler` above simply echoes the audio back to the client.
* The `StreamHandler` class has two methods: `receive` and `emit`. The `receive` method is called when a new frame is received from the client, and the `emit` method returns the next frame to send to the client.
* An audio frame is represented as a tuple of (frame_rate, audio_samples) where `audio_samples` is a numpy array of shape (num_channels, num_samples).
* You can also specify the audio layout ("mono" or "stereo") in the emit method by retuning it as the third element of the tuple. If not specified, the default is "mono".
* The `time_limit` parameter is the maximum time in seconds the conversation will run. If the time limit is reached, the audio stream will stop.
* The `emit` method SHOULD NOT block. If a frame is not ready to be sent, the method should return None.
## Deployment
When deploying in a cloud environment (like Hugging Face Spaces, EC2, etc), you need to set up a TURN server to relay the WebRTC traffic.
The easiest way to do this is to use a service like Twilio.
```python
from twilio.rest import Client
import os
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
with gr.Blocks() as demo:
...
rtc = WebRTC(rtc_configuration=rtc_configuration, ...)
...
```
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
##
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.ParamViewer(value=_docs["WebRTC"]["members"]["__init__"], linkify=[])
demo.load(
None,
js=r"""function() {
const refs = {};
const user_fn_refs = {
WebRTC: [], };
requestAnimationFrame(() => {
Object.entries(user_fn_refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}-user-fn`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
Object.entries(refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
})
}
""",
)
demo.launch()

367
demo/app_.py
View File

@@ -1,367 +0,0 @@
import os
import gradio as gr
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "The height of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"width": {
"type": "int | str | None",
"default": "None",
"description": "The width of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"label": {
"type": "str | None",
"default": "None",
"description": "the label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.",
},
"min_width": {
"type": "int",
"default": "160",
"description": "minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.",
},
"interactive": {
"type": "bool | None",
"default": "None",
"description": "if True, will allow users to upload a video; if False, can only be used to display videos. If not provided, this is inferred based on whether the component is used as an input or output.",
},
"visible": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "an optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"elem_classes": {
"type": "list[str] | str | None",
"default": "None",
"description": "an optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"render": {
"type": "bool",
"default": "True",
"description": "if False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.",
},
"key": {
"type": "int | str | None",
"default": "None",
"description": "if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.",
},
"mirror_webcam": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}
abs_path = os.path.join(os.path.dirname(__file__), "css.css")
with gr.Blocks(
css_paths=abs_path,
theme=gr.themes.Default(
font_mono=[
gr.themes.GoogleFont("Inconsolata"),
"monospace",
],
),
) as demo:
gr.Markdown(
"""
<h1 style='text-align: center; margin-bottom: 1rem'> Gradio WebRTC ⚡️ </h1>
<div style="display: flex; flex-direction: row; justify-content: center">
<img style="display: block; padding-right: 5px; height: 20px;" alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.6%20-%20orange">
<a href="https://github.com/freddyaboulton/gradio-webrtc" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/github-white?logo=github&logoColor=black"></a>
</div>
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
## Installation
```bash
pip install gradio_webrtc
```
## Examples:
1. [Object Detection from Webcam with YOLOv10](https://huggingface.co/spaces/freddyaboulton/webrtc-yolov10n) 📷
2. [Streaming Object Detection from Video with RT-DETR](https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc) 🎥
3. [Text-to-Speech](https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc) 🗣️
4. [Conversational AI](https://huggingface.co/spaces/freddyaboulton/omni-mini-webrtc) 🤖🗣️
## Usage
The WebRTC component supports the following three use cases:
1. [Streaming video from the user webcam to the server and back](#h-streaming-video-from-the-user-webcam-to-the-server-and-back)
2. [Streaming Video from the server to the client](#h-streaming-video-from-the-server-to-the-client)
3. [Streaming Audio from the server to the client](#h-streaming-audio-from-the-server-to-the-client)
4. [Streaming Audio from the client to the server and back (conversational AI)](#h-conversational-ai)
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
def detection(image, conf_threshold=0.3):
... your detection code here ...
with gr.Blocks() as demo:
image = WebRTC(label="Stream", mode="send-receive", modality="video")
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection,
inputs=[image, conf_threshold],
outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()
```
* Set the `mode` parameter to `send-receive` and `modality` to "video".
* The `stream` event's `fn` parameter is a function that receives the next frame from the webcam
as a **numpy array** and returns the processed frame also as a **numpy array**.
* Numpy arrays are in (height, width, 3) format where the color channels are in RGB format.
* The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component.
* The `time_limit` parameter is the maximum time in seconds the video stream will run. If the time limit is reached, the video stream will stop.
## Streaming Video from the server to the client
```python
import gradio as gr
from gradio_webrtc import WebRTC
import cv2
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
output_video = WebRTC(label="Video Stream", mode="receive", modality="video")
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video],
trigger=button.click
)
if __name__ == "__main__":
demo.launch()
```
* Set the "mode" parameter to "receive" and "modality" to "video".
* The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**.
* The only output allowed is the WebRTC component.
* The `trigger` parameter the gradio event that will trigger the webrtc connection. In this case, the button click event.
## Streaming Audio from the Server to the Client
```python
import gradio as gr
from pydub import AudioSegment
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file("/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav")
yield (segment.frame_rate, np.array(segment.get_array_of_samples()).reshape(1, -1))
with gr.Blocks() as demo:
audio = WebRTC(label="Stream", mode="receive", modality="audio")
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio],
trigger=button.click
)
```
* Set the "mode" parameter to "receive" and "modality" to "audio".
* The `stream` event's `fn` parameter is a generator function that yields the next audio segment as a tuple of (frame_rate, audio_samples).
* The numpy array should be of shape (1, num_samples).
* The `outputs` parameter should be a list with the WebRTC component as the only element.
## Conversational AI
```python
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC, StreamHandler
from queue import Queue
import time
class EchoHandler(StreamHandler):
def __init__(self) -> None:
super().__init__()
self.queue = Queue()
def receive(self, frame: tuple[int, np.ndarray] | np.ndarray) -> None:
self.queue.put(frame)
def emit(self) -> None:
return self.queue.get()
with gr.Blocks() as demo:
with gr.Column():
with gr.Group():
audio = WebRTC(
label="Stream",
rtc_configuration=None,
mode="send-receive",
modality="audio",
)
audio.stream(fn=EchoHandler(), inputs=[audio], outputs=[audio], time_limit=15)
if __name__ == "__main__":
demo.launch()
```
* Instead of passing a function to the `stream` event's `fn` parameter, pass a `StreamHandler` implementation. The `StreamHandler` above simply echoes the audio back to the client.
* The `StreamHandler` class has two methods: `receive` and `emit`. The `receive` method is called when a new frame is received from the client, and the `emit` method returns the next frame to send to the client.
* An audio frame is represented as a tuple of (frame_rate, audio_samples) where `audio_samples` is a numpy array of shape (num_channels, num_samples).
* You can also specify the audio layout ("mono" or "stereo") in the emit method by retuning it as the third element of the tuple. If not specified, the default is "mono".
* The `time_limit` parameter is the maximum time in seconds the conversation will run. If the time limit is reached, the audio stream will stop.
* The `emit` method SHOULD NOT block. If a frame is not ready to be sent, the method should return None.
## Deployment
When deploying in a cloud environment (like Hugging Face Spaces, EC2, etc), you need to set up a TURN server to relay the WebRTC traffic.
The easiest way to do this is to use a service like Twilio.
```python
from twilio.rest import Client
import os
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
with gr.Blocks() as demo:
...
rtc = WebRTC(rtc_configuration=rtc_configuration, ...)
...
```
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
##
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.ParamViewer(value=_docs["WebRTC"]["members"]["__init__"], linkify=[])
demo.load(
None,
js=r"""function() {
const refs = {};
const user_fn_refs = {
WebRTC: [], };
requestAnimationFrame(() => {
Object.entries(user_fn_refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}-user-fn`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
Object.entries(refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
})
}
""",
)
demo.launch()

73
demo/app_orig.py
View File

@@ -1,73 +0,0 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from huggingface_hub import hf_hub_download
from inference import YOLOv10
from twilio.rest import Client
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def detection(image, conf_threshold=0.3):
image = cv2.resize(image, (model.input_width, model.input_height))
new_image = model.detect_objects(image, conf_threshold)
return cv2.resize(new_image, (500, 500))
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks(css=css) as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
</h1>
"""
)
gr.HTML(
"""
<h3 style='text-align: center'>
<a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
</h3>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()

71
demo/audio_out.py
View File

@@ -1,71 +0,0 @@
import os
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC
from pydub import AudioSegment
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file(
"/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav"
)
yield (
segment.frame_rate,
np.array(segment.get_array_of_samples()).reshape(1, -1),
)
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Audio Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
audio = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="audio",
)
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio], trigger=button.click
)
if __name__ == "__main__":
demo.launch()

64
demo/audio_out_2.py
View File

@@ -1,64 +0,0 @@
import os
import time
import gradio as gr
import numpy as np
from gradio_webrtc import WebRTC
from pydub import AudioSegment
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file(
"/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav"
)
yield (
segment.frame_rate,
np.array(segment.get_array_of_samples()).reshape(1, -1),
)
time.sleep(3.5)
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Audio Streaming (Powered by WebRaTC ⚡️)
</h1>
"""
)
with gr.Row():
with gr.Column():
gr.Slider()
with gr.Column():
# audio = gr.Audio(interactive=False)
audio = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="audio",
)
if __name__ == "__main__":
demo.launch()

161
demo/css.css
View File

@@ -1,161 +0,0 @@
html {
font-family: Inter;
font-size: 16px;
font-weight: 400;
line-height: 1.5;
-webkit-text-size-adjust: 100%;
background: #fff;
color: #323232;
-webkit-font-smoothing: antialiased;
-moz-osx-font-smoothing: grayscale;
text-rendering: optimizeLegibility;
}
:root {
--space: 1;
--vspace: calc(var(--space) * 1rem);
--vspace-0: calc(3 * var(--space) * 1rem);
--vspace-1: calc(2 * var(--space) * 1rem);
--vspace-2: calc(1.5 * var(--space) * 1rem);
--vspace-3: calc(0.5 * var(--space) * 1rem);
}
.app {
max-width: 748px !important;
}
.prose p {
margin: var(--vspace) 0;
line-height: var(--vspace * 2);
font-size: 1rem;
}
code {
font-family: "Inconsolata", sans-serif;
font-size: 16px;
}
h1,
h1 code {
font-weight: 400;
line-height: calc(2.5 / var(--space) * var(--vspace));
}
h1 code {
background: none;
border: none;
letter-spacing: 0.05em;
padding-bottom: 5px;
position: relative;
padding: 0;
}
h2 {
margin: var(--vspace-1) 0 var(--vspace-2) 0;
line-height: 1em;
}
h3,
h3 code {
margin: var(--vspace-1) 0 var(--vspace-2) 0;
line-height: 1em;
}
h4,
h5,
h6 {
margin: var(--vspace-3) 0 var(--vspace-3) 0;
line-height: var(--vspace);
}
.bigtitle,
h1,
h1 code {
font-size: calc(8px * 4.5);
word-break: break-word;
}
.title,
h2,
h2 code {
font-size: calc(8px * 3.375);
font-weight: lighter;
word-break: break-word;
border: none;
background: none;
}
.subheading1,
h3,
h3 code {
font-size: calc(8px * 1.8);
font-weight: 600;
border: none;
background: none;
letter-spacing: 0.1em;
text-transform: uppercase;
}
h2 code {
padding: 0;
position: relative;
letter-spacing: 0.05em;
}
blockquote {
font-size: calc(8px * 1.1667);
font-style: italic;
line-height: calc(1.1667 * var(--vspace));
margin: var(--vspace-2) var(--vspace-2);
}
.subheading2,
h4 {
font-size: calc(8px * 1.4292);
text-transform: uppercase;
font-weight: 600;
}
.subheading3,
h5 {
font-size: calc(8px * 1.2917);
line-height: calc(1.2917 * var(--vspace));
font-weight: lighter;
text-transform: uppercase;
letter-spacing: 0.15em;
}
h6 {
font-size: calc(8px * 1.1667);
font-size: 1.1667em;
font-weight: normal;
font-style: italic;
font-family: "le-monde-livre-classic-byol", serif !important;
letter-spacing: 0px !important;
}
#start .md > *:first-child {
margin-top: 0;
}
h2 + h3 {
margin-top: 0;
}
.md hr {
border: none;
border-top: 1px solid var(--block-border-color);
margin: var(--vspace-2) 0 var(--vspace-2) 0;
}
.prose ul {
margin: var(--vspace-2) 0 var(--vspace-1) 0;
}
.gap {
gap: 0;
}
.md-custom {
overflow: hidden;
}

99
demo/docs.py
View File

@@ -1,99 +0,0 @@
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "The height of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"width": {
"type": "int | str | None",
"default": "None",
"description": "The width of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"label": {
"type": "str | None",
"default": "None",
"description": "the label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.",
},
"min_width": {
"type": "int",
"default": "160",
"description": "minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.",
},
"interactive": {
"type": "bool | None",
"default": "None",
"description": "if True, will allow users to upload a video; if False, can only be used to display videos. If not provided, this is inferred based on whether the component is used as an input or output.",
},
"visible": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "an optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"elem_classes": {
"type": "list[str] | str | None",
"default": "None",
"description": "an optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"render": {
"type": "bool",
"default": "True",
"description": "if False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.",
},
"key": {
"type": "int | str | None",
"default": "None",
"description": "if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.",
},
"mirror_webcam": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
"postprocess": {
"value": {
"type": "typing.Any",
"description": "Expects a {str} or {pathlib.Path} filepath to a video which is displayed, or a {Tuple[str | pathlib.Path, str | pathlib.Path | None]} where the first element is a filepath to a video and the second element is an optional filepath to a subtitle file.",
}
},
"preprocess": {
"return": {
"type": "str",
"description": "Passes the uploaded video as a `str` filepath or URL whose extension can be modified by `format`.",
},
"value": None,
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}

15
demo/echo_audio/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Echo Audio
emoji: 🪩
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Simple echo stream - simplest FastRTC demo
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

45
demo/echo_audio/app.py Normal file
View File

@@ -0,0 +1,45 @@
import numpy as np
from fastapi import FastAPI
from fastapi.responses import RedirectResponse
from fastrtc import ReplyOnPause, Stream, get_twilio_turn_credentials
from gradio.utils import get_space
def detection(audio: tuple[int, np.ndarray]):
# Implement any iterator that yields audio
# See "LLM Voice Chat" for a more complete example
yield audio
stream = Stream(
handler=ReplyOnPause(detection),
modality="audio",
mode="send-receive",
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
)
app = FastAPI()
stream.mount(app)
@app.get("/")
async def index():
return RedirectResponse(
url="/ui" if not get_space() else "https://fastrtc-echo-audio.hf.space/ui/"
)
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
stream.fastphone(port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

3
demo/echo_audio/requirements.txt Normal file
View File

@@ -0,0 +1,3 @@
fastrtc[vad]
twilio
python-dotenv

61
demo/echo_conversation.py
View File

@@ -1,61 +0,0 @@
import logging
from queue import Queue
import gradio as gr
import numpy as np
from gradio_webrtc import StreamHandler, WebRTC
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.StreamHandler()
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("gradio_webrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
class EchoHandler(StreamHandler):
def __init__(self) -> None:
super().__init__()
self.queue = Queue()
def receive(self, frame: tuple[int, np.ndarray] | np.ndarray) -> None:
self.queue.put(frame)
def emit(self) -> None:
return self.queue.get()
def copy(self) -> StreamHandler:
return EchoHandler()
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Conversational AI (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Column():
with gr.Group():
audio = WebRTC(
label="Stream",
rtc_configuration=None,
mode="send-receive",
modality="audio",
)
audio.stream(fn=EchoHandler(), inputs=[audio], outputs=[audio], time_limit=15)
if __name__ == "__main__":
demo.launch()

15
demo/gemini_audio_video/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Gemini Audio Video
emoji: ♊️
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Gemini understands audio and video!
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GEMINI_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

207
demo/gemini_audio_video/app.py Normal file
View File

@@ -0,0 +1,207 @@
import asyncio
import base64
import os
import time
from io import BytesIO
import gradio as gr
from gradio.utils import get_space
import numpy as np
from google import genai
from dotenv import load_dotenv
from fastrtc import (
AsyncAudioVideoStreamHandler,
Stream,
get_twilio_turn_credentials,
WebRTC,
)
from PIL import Image
load_dotenv()
def encode_audio(data: np.ndarray) -> dict:
"""Encode Audio data to send to the server"""
return {
"mime_type": "audio/pcm",
"data": base64.b64encode(data.tobytes()).decode("UTF-8"),
}
def encode_image(data: np.ndarray) -> dict:
with BytesIO() as output_bytes:
pil_image = Image.fromarray(data)
pil_image.save(output_bytes, "JPEG")
bytes_data = output_bytes.getvalue()
base64_str = str(base64.b64encode(bytes_data), "utf-8")
return {"mime_type": "image/jpeg", "data": base64_str}
class GeminiHandler(AsyncAudioVideoStreamHandler):
def __init__(
self,
) -> None:
super().__init__(
"mono",
output_sample_rate=24000,
output_frame_size=480,
input_sample_rate=16000,
)
self.audio_queue = asyncio.Queue()
self.video_queue = asyncio.Queue()
self.quit = asyncio.Event()
self.session = None
self.last_frame_time = 0
self.quit = asyncio.Event()
def copy(self) -> "GeminiHandler":
return GeminiHandler()
async def start_up(self):
client = genai.Client(
api_key=os.getenv("GEMINI_API_KEY"), http_options={"api_version": "v1alpha"}
)
config = {"response_modalities": ["AUDIO"]}
try:
async with client.aio.live.connect(
model="gemini-2.0-flash-exp", config=config
) as session:
self.session = session
print("set session")
while not self.quit.is_set():
turn = self.session.receive()
async for response in turn:
if data := response.data:
audio = np.frombuffer(data, dtype=np.int16).reshape(1, -1)
self.audio_queue.put_nowait(audio)
except Exception as e:
import traceback
traceback.print_exc()
async def video_receive(self, frame: np.ndarray):
try:
print("out")
if self.session:
print("here")
# send image every 1 second
print(time.time() - self.last_frame_time)
if time.time() - self.last_frame_time > 1:
self.last_frame_time = time.time()
print("sending image")
await self.session.send(input=encode_image(frame))
print("sent image")
if self.latest_args[1] is not None:
print("sending image2")
await self.session.send(input=encode_image(self.latest_args[1]))
print("sent image2")
except Exception as e:
print(e)
import traceback
traceback.print_exc()
self.video_queue.put_nowait(frame)
async def video_emit(self):
return await self.video_queue.get()
async def receive(self, frame: tuple[int, np.ndarray]) -> None:
_, array = frame
array = array.squeeze()
audio_message = encode_audio(array)
if self.session:
try:
await self.session.send(input=audio_message)
except Exception as e:
print(e)
import traceback
traceback.print_exc()
async def emit(self):
array = await self.audio_queue.get()
return (self.output_sample_rate, array)
async def shutdown(self) -> None:
if self.session:
self.quit.set()
await self.session._websocket.close()
self.quit.clear()
stream = Stream(
handler=GeminiHandler(),
modality="audio-video",
mode="send-receive",
rtc_configuration=get_twilio_turn_credentials()
if get_space() == "spaces"
else None,
time_limit=90 if get_space() else None,
additional_inputs=[
gr.Image(label="Image", type="numpy", sources=["upload", "clipboard"])
],
ui_args={
"icon": "https://www.gstatic.com/lamda/images/gemini_favicon_f069958c85030456e93de685481c559f160ea06b.png",
"pulse_color": "rgb(35, 157, 225)",
"icon_button_color": "rgb(35, 157, 225)",
"title": "Gemini Audio Video Chat",
},
)
css = """
#video-source {max-width: 600px !important; max-height: 600 !important;}
"""
with gr.Blocks(css=css) as demo:
gr.HTML(
"""
<div style='display: flex; align-items: center; justify-content: center; gap: 20px'>
<div style="background-color: var(--block-background-fill); border-radius: 8px">
<img src="https://www.gstatic.com/lamda/images/gemini_favicon_f069958c85030456e93de685481c559f160ea06b.png" style="width: 100px; height: 100px;">
</div>
<div>
<h1>Gen AI SDK Voice Chat</h1>
<p>Speak with Gemini using real-time audio + video streaming</p>
<p>Powered by <a href="https://gradio.app/">Gradio</a> and <a href=https://freddyaboulton.github.io/gradio-webrtc/">WebRTC</a>⚡️</p>
<p>Get an API Key <a href="https://support.google.com/googleapi/answer/6158862?hl=en">here</a></p>
</div>
</div>
"""
)
with gr.Row() as row:
with gr.Column():
webrtc = WebRTC(
label="Video Chat",
modality="audio-video",
mode="send-receive",
elem_id="video-source",
rtc_configuration=get_twilio_turn_credentials()
if get_space() == "spaces"
else None,
icon="https://www.gstatic.com/lamda/images/gemini_favicon_f069958c85030456e93de685481c559f160ea06b.png",
pulse_color="rgb(35, 157, 225)",
icon_button_color="rgb(35, 157, 225)",
)
with gr.Column():
image_input = gr.Image(
label="Image", type="numpy", sources=["upload", "clipboard"]
)
webrtc.stream(
GeminiHandler(),
inputs=[webrtc, image_input],
outputs=[webrtc],
time_limit=60 if get_space() else None,
concurrency_limit=2 if get_space() else None,
)
stream.ui = demo
if __name__ == "__main__":
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
raise ValueError("Phone mode not supported for this demo")
else:
stream.ui.launch(server_port=7860)

4
demo/gemini_audio_video/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc
python-dotenv
google-genai
twilio

15
demo/hello_computer/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Hello Computer
emoji: 💻
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Say computer before asking your question
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|SAMBANOVA_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

15
demo/hello_computer/README_gradio.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Hello Computer (Gradio)
emoji: 💻
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Say computer (Gradio)
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|SAMBANOVA_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

153
demo/hello_computer/app.py Normal file
View File

@@ -0,0 +1,153 @@
import base64
import json
import os
from pathlib import Path
import gradio as gr
import numpy as np
import openai
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse
from fastrtc import (
AdditionalOutputs,
ReplyOnStopWords,
Stream,
WebRTCError,
get_stt_model,
get_twilio_turn_credentials,
)
from gradio.utils import get_space
from pydantic import BaseModel
load_dotenv()
curr_dir = Path(__file__).parent
client = openai.OpenAI(
api_key=os.environ.get("SAMBANOVA_API_KEY"),
base_url="https://api.sambanova.ai/v1",
)
model = get_stt_model()
def response(
audio: tuple[int, np.ndarray],
gradio_chatbot: list[dict] | None = None,
conversation_state: list[dict] | None = None,
):
gradio_chatbot = gradio_chatbot or []
conversation_state = conversation_state or []
try:
text = model.stt(audio)
print("STT in handler", text)
sample_rate, array = audio
gradio_chatbot.append(
{"role": "user", "content": gr.Audio((sample_rate, array.squeeze()))}
)
yield AdditionalOutputs(gradio_chatbot, conversation_state)
conversation_state.append({"role": "user", "content": text})
request = client.chat.completions.create(
model="Meta-Llama-3.2-3B-Instruct",
messages=conversation_state, # type: ignore
temperature=0.1,
top_p=0.1,
)
response = {"role": "assistant", "content": request.choices[0].message.content}
except Exception as e:
import traceback
traceback.print_exc()
raise WebRTCError(str(e) + "\n" + traceback.format_exc())
conversation_state.append(response)
gradio_chatbot.append(response)
yield AdditionalOutputs(gradio_chatbot, conversation_state)
chatbot = gr.Chatbot(type="messages", value=[])
state = gr.State(value=[])
stream = Stream(
ReplyOnStopWords(
response, # type: ignore
stop_words=["computer"],
input_sample_rate=16000,
),
mode="send",
modality="audio",
additional_inputs=[chatbot, state],
additional_outputs=[chatbot, state],
additional_outputs_handler=lambda *a: (a[2], a[3]),
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
)
app = FastAPI()
stream.mount(app)
class Message(BaseModel):
role: str
content: str
class InputData(BaseModel):
webrtc_id: str
chatbot: list[Message]
state: list[Message]
@app.get("/")
async def _():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (curr_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content)
@app.post("/input_hook")
async def _(data: InputData):
body = data.model_dump()
stream.set_input(data.webrtc_id, body["chatbot"], body["state"])
def audio_to_base64(file_path):
audio_format = "wav"
with open(file_path, "rb") as audio_file:
encoded_audio = base64.b64encode(audio_file.read()).decode("utf-8")
return f"data:audio/{audio_format};base64,{encoded_audio}"
@app.get("/outputs")
async def _(webrtc_id: str):
async def output_stream():
async for output in stream.output_stream(webrtc_id):
chatbot = output.args[0]
state = output.args[1]
data = {
"message": state[-1],
"audio": audio_to_base64(chatbot[-1]["content"].value["path"])
if chatbot[-1]["role"] == "user"
else None,
}
yield f"event: output\ndata: {json.dumps(data)}\n\n"
return StreamingResponse(output_stream(), media_type="text/event-stream")
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
raise ValueError("Phone mode not supported")
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

486
demo/hello_computer/index.html Normal file
View File

@@ -0,0 +1,486 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Hello Computer 💻</title>
<style>
body {
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
background-color: #f8f9fa;
color: #1a1a1a;
margin: 0;
padding: 20px;
height: 100vh;
box-sizing: border-box;
}
.container {
max-width: 800px;
margin: 0 auto;
height: calc(100% - 100px);
}
.logo {
text-align: center;
margin-bottom: 40px;
}
.chat-container {
background: white;
border-radius: 8px;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
padding: 20px;
height: 90%;
box-sizing: border-box;
display: flex;
flex-direction: column;
}
.chat-messages {
flex-grow: 1;
overflow-y: auto;
margin-bottom: 20px;
padding: 10px;
}
.message {
margin-bottom: 20px;
padding: 12px;
border-radius: 8px;
font-size: 14px;
line-height: 1.5;
}
.message.user {
background-color: #e9ecef;
margin-left: 20%;
}
.message.assistant {
background-color: #f1f3f5;
margin-right: 20%;
}
.controls {
text-align: center;
margin-top: 20px;
}
button {
background-color: #0066cc;
color: white;
border: none;
padding: 12px 24px;
font-family: inherit;
font-size: 14px;
cursor: pointer;
transition: all 0.3s;
border-radius: 4px;
font-weight: 500;
}
button:hover {
background-color: #0052a3;
}
#audio-output {
display: none;
}
.icon-with-spinner {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.spinner {
width: 20px;
height: 20px;
border: 2px solid #ffffff;
border-top-color: transparent;
border-radius: 50%;
animation: spin 1s linear infinite;
flex-shrink: 0;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
.pulse-container {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.pulse-circle {
width: 20px;
height: 20px;
border-radius: 50%;
background-color: #ffffff;
opacity: 0.2;
flex-shrink: 0;
transform: translateX(-0%) scale(var(--audio-level, 1));
transition: transform 0.1s ease;
}
/* Add styles for typing indicator */
.typing-indicator {
padding: 8px;
background-color: #f1f3f5;
border-radius: 8px;
margin-bottom: 10px;
display: none;
}
.dots {
display: inline-flex;
gap: 4px;
}
.dot {
width: 8px;
height: 8px;
background-color: #0066cc;
border-radius: 50%;
animation: pulse 1.5s infinite;
opacity: 0.5;
}
.dot:nth-child(2) {
animation-delay: 0.5s;
}
.dot:nth-child(3) {
animation-delay: 1s;
}
@keyframes pulse {
0%,
100% {
opacity: 0.5;
transform: scale(1);
}
50% {
opacity: 1;
transform: scale(1.2);
}
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div class="container">
<div class="logo">
<h1>Hello Computer 💻</h1>
<h2 style="font-size: 1.2em; color: #666; margin-top: 10px;">Say 'Computer' before asking your question</h2>
</div>
<div class="chat-container">
<div class="chat-messages" id="chat-messages"></div>
<div class="typing-indicator" id="typing-indicator">
<div class="dots">
<div class="dot"></div>
<div class="dot"></div>
<div class="dot"></div>
</div>
</div>
</div>
<div class="controls">
<button id="start-button">Start Conversation</button>
</div>
</div>
<audio id="audio-output"></audio>
<script>
let peerConnection;
let webrtc_id;
const startButton = document.getElementById('start-button');
const chatMessages = document.getElementById('chat-messages');
let audioLevel = 0;
let animationFrame;
let audioContext, analyser, audioSource;
let messages = [];
let eventSource;
function updateButtonState() {
const button = document.getElementById('start-button');
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
button.innerHTML = `
<div class="icon-with-spinner">
<div class="spinner"></div>
<span>Connecting...</span>
</div>
`;
} else if (peerConnection && peerConnection.connectionState === 'connected') {
button.innerHTML = `
<div class="pulse-container">
<div class="pulse-circle"></div>
<span>Stop Conversation</span>
</div>
`;
} else {
button.innerHTML = 'Start Conversation';
}
}
function setupAudioVisualization(stream) {
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
audioSource = audioContext.createMediaStreamSource(stream);
audioSource.connect(analyser);
analyser.fftSize = 64;
const dataArray = new Uint8Array(analyser.frequencyBinCount);
function updateAudioLevel() {
analyser.getByteFrequencyData(dataArray);
const average = Array.from(dataArray).reduce((a, b) => a + b, 0) / dataArray.length;
audioLevel = average / 255;
const pulseCircle = document.querySelector('.pulse-circle');
if (pulseCircle) {
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
}
animationFrame = requestAnimationFrame(updateAudioLevel);
}
updateAudioLevel();
}
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.className = 'toast error';
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
function handleMessage(event) {
const eventJson = JSON.parse(event.data);
const typingIndicator = document.getElementById('typing-indicator');
if (eventJson.type === "error") {
showError(eventJson.message);
} else if (eventJson.type === "send_input") {
fetch('/input_hook', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({
webrtc_id: webrtc_id,
chatbot: messages,
state: messages
})
});
} else if (eventJson.type === "log") {
if (eventJson.data === "pause_detected") {
typingIndicator.style.display = 'block';
chatMessages.scrollTop = chatMessages.scrollHeight;
} else if (eventJson.data === "response_starting") {
typingIndicator.style.display = 'none';
}
}
}
async function setupWebRTC() {
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({
audio: true
});
setupAudioVisualization(stream);
stream.getTracks().forEach(track => {
peerConnection.addTrack(track, stream);
});
const dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = handleMessage;
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
peerConnection.addEventListener('connectionstatechange', () => {
console.log('connectionstatechange', peerConnection.connectionState);
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
updateButtonState();
});
webrtc_id = Math.random().toString(36).substring(7);
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
return;
}
await peerConnection.setRemoteDescription(serverResponse);
eventSource = new EventSource('/outputs?webrtc_id=' + webrtc_id);
eventSource.addEventListener("output", (event) => {
const eventJson = JSON.parse(event.data);
console.log(eventJson);
messages.push(eventJson.message);
addMessage(eventJson.message.role, eventJson.audio ?? eventJson.message.content);
});
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
}
}
function addMessage(role, content) {
const messageDiv = document.createElement('div');
messageDiv.classList.add('message', role);
if (role === 'user') {
// Create audio element for user messages
const audio = document.createElement('audio');
audio.controls = true;
audio.src = content;
messageDiv.appendChild(audio);
} else {
// Text content for assistant messages
messageDiv.textContent = content;
}
chatMessages.appendChild(messageDiv);
chatMessages.scrollTop = chatMessages.scrollHeight;
}
function stop() {
if (eventSource) {
eventSource.close();
eventSource = null;
}
if (animationFrame) {
cancelAnimationFrame(animationFrame);
}
if (audioContext) {
audioContext.close();
audioContext = null;
analyser = null;
audioSource = null;
}
if (peerConnection) {
if (peerConnection.getTransceivers) {
peerConnection.getTransceivers().forEach(transceiver => {
if (transceiver.stop) {
transceiver.stop();
}
});
}
if (peerConnection.getSenders) {
peerConnection.getSenders().forEach(sender => {
if (sender.track && sender.track.stop) sender.track.stop();
});
}
peerConnection.close();
}
updateButtonState();
audioLevel = 0;
}
startButton.addEventListener('click', () => {
if (!peerConnection || peerConnection.connectionState !== 'connected') {
setupWebRTC();
} else {
stop();
}
});
</script>
</body>
</html>

4
demo/hello_computer/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc[stopword]
python-dotenv
openai
twilio

16
demo/llama_code_editor/README.md Normal file
View File

@@ -0,0 +1,16 @@
---
title: Llama Code Editor
emoji: 🦙
colorFrom: indigo
colorTo: pink
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Create interactive HTML web pages with your voice
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN,
secret|SAMBANOVA_API_KEY, secret|GROQ_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

45
demo/llama_code_editor/app.py Normal file
View File

@@ -0,0 +1,45 @@
from fastapi import FastAPI
from fastapi.responses import RedirectResponse
from fastrtc import Stream
from gradio.utils import get_space
try:
from demo.llama_code_editor.handler import (
CodeHandler,
)
from demo.llama_code_editor.ui import demo as ui
except (ImportError, ModuleNotFoundError):
from handler import CodeHandler
from ui import demo as ui
stream = Stream(
handler=CodeHandler,
modality="audio",
mode="send-receive",
concurrency_limit=10 if get_space() else None,
time_limit=90 if get_space() else None,
)
stream.ui = ui
app = FastAPI()
@app.get("/")
async def _():
url = "/ui" if not get_space() else "https://fastrtc-llama-code-editor.hf.space/ui/"
return RedirectResponse(url)
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860, server_name="0.0.0.0")
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

37
demo/llama_code_editor/assets/sandbox.html Normal file
View File

@@ -0,0 +1,37 @@
<div style="
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
min-height: 400px;
background: linear-gradient(135deg, #f5f7fa 0%, #e4e8ec 100%);
border-radius: 8px;
border: 2px dashed #cbd5e1;
padding: 2rem;
text-align: center;
color: #64748b;
font-family: system-ui, -apple-system, sans-serif;
">
<div style="
width: 80px;
height: 80px;
margin-bottom: 1.5rem;
border: 3px solid #cbd5e1;
border-radius: 12px;
position: relative;
">
<div style="
position: absolute;
top: 50%;
left: 50%;
transform: translate(-50%, -50%);
font-size: 2rem;
">📦</div>
</div>
<h2 style="
margin: 0 0 0.5rem 0;
font-size: 1.5rem;
font-weight: 600;
color: #475569;
">No Application Created</h2>
</div>

60
demo/llama_code_editor/assets/spinner.html Normal file
View File

@@ -0,0 +1,60 @@
<div style="
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
min-height: 400px;
background: linear-gradient(135deg, #f8fafc 0%, #f1f5f9 100%);
border-radius: 8px;
padding: 2rem;
text-align: center;
font-family: system-ui, -apple-system, sans-serif;
">
<!-- Spinner container -->
<div style="
position: relative;
width: 64px;
height: 64px;
margin-bottom: 1.5rem;
">
<!-- Static ring -->
<div style="
position: absolute;
width: 100%;
height: 100%;
border: 4px solid #e2e8f0;
border-radius: 50%;
"></div>
<!-- Animated spinner -->
<div style="
position: absolute;
width: 100%;
height: 100%;
border: 4px solid transparent;
border-top-color: #3b82f6;
border-radius: 50%;
animation: spin 1s linear infinite;
"></div>
</div>
<!-- Text content -->
<h2 style="
margin: 0 0 0.5rem 0;
font-size: 1.25rem;
font-weight: 600;
color: #475569;
">Generating your application...</h2>
<p style="
margin: 0;
font-size: 0.875rem;
color: #64748b;
">This may take a few moments</p>
<style>
@keyframes spin {
0% { transform: rotate(0deg); }
100% { transform: rotate(360deg); }
}
</style>
</div>

73
demo/llama_code_editor/handler.py Normal file
View File

@@ -0,0 +1,73 @@
import base64
import os
import re
from pathlib import Path
import numpy as np
import openai
from dotenv import load_dotenv
from fastrtc import (
AdditionalOutputs,
ReplyOnPause,
audio_to_bytes,
)
from groq import Groq
load_dotenv()
groq_client = Groq(api_key=os.environ.get("GROQ_API_KEY"))
client = openai.OpenAI(
api_key=os.environ.get("SAMBANOVA_API_KEY"),
base_url="https://api.sambanova.ai/v1",
)
path = Path(__file__).parent / "assets"
spinner_html = open(path / "spinner.html").read()
system_prompt = "You are an AI coding assistant. Your task is to write single-file HTML applications based on a user's request. Only return the necessary code. Include all necessary imports and styles. You may also be asked to edit your original response."
user_prompt = "Please write a single-file HTML application to fulfill the following request.\nThe message:{user_message}\nCurrent code you have written:{code}"
def extract_html_content(text):
"""
Extract content including HTML tags.
"""
match = re.search(r"<!DOCTYPE html>.*?</html>", text, re.DOTALL)
return match.group(0) if match else None
def display_in_sandbox(code):
encoded_html = base64.b64encode(code.encode("utf-8")).decode("utf-8")
data_uri = f"data:text/html;charset=utf-8;base64,{encoded_html}"
return f'<iframe src="{data_uri}" width="100%" height="600px"></iframe>'
def generate(user_message: tuple[int, np.ndarray], history: list[dict], code: str):
yield AdditionalOutputs(history, spinner_html)
text = groq_client.audio.transcriptions.create(
file=("audio-file.mp3", audio_to_bytes(user_message)),
model="whisper-large-v3-turbo",
response_format="verbose_json",
).text
user_msg_formatted = user_prompt.format(user_message=text, code=code)
history.append({"role": "user", "content": user_msg_formatted})
response = client.chat.completions.create(
model="Meta-Llama-3.1-70B-Instruct",
messages=history, # type: ignore
temperature=0.1,
top_p=0.1,
)
output = response.choices[0].message.content
html_code = extract_html_content(output)
history.append({"role": "assistant", "content": output})
yield AdditionalOutputs(history, html_code)
CodeHandler = ReplyOnPause(generate) # type: ignore

5
demo/llama_code_editor/requirements.in Normal file
View File

@@ -0,0 +1,5 @@
fastrtc[vad]
groq
openai
python-dotenv
twilio

295
demo/llama_code_editor/requirements.txt Normal file
View File

@@ -0,0 +1,295 @@
# This file was autogenerated by uv via the following command:
# uv pip compile demo/llama_code_editor/requirements.in -o demo/llama_code_editor/requirements.txt
aiofiles==23.2.1
# via gradio
aiohappyeyeballs==2.4.6
# via aiohttp
aiohttp==3.11.12
# via
# aiohttp-retry
# twilio
aiohttp-retry==2.9.1
# via twilio
aioice==0.9.0
# via aiortc
aiortc==1.10.1
# via fastrtc
aiosignal==1.3.2
# via aiohttp
annotated-types==0.7.0
# via pydantic
anyio==4.6.2.post1
# via
# gradio
# groq
# httpx
# openai
# starlette
attrs==25.1.0
# via aiohttp
audioread==3.0.1
# via librosa
av==12.3.0
# via aiortc
certifi==2024.8.30
# via
# httpcore
# httpx
# requests
cffi==1.17.1
# via
# aiortc
# cryptography
# pylibsrtp
# soundfile
charset-normalizer==3.4.0
# via requests
click==8.1.7
# via
# typer
# uvicorn
coloredlogs==15.0.1
# via onnxruntime
cryptography==43.0.3
# via
# aiortc
# pyopenssl
decorator==5.1.1
# via librosa
distro==1.9.0
# via
# groq
# openai
dnspython==2.7.0
# via aioice
fastapi==0.115.5
# via gradio
fastrtc==0.0.2.post4
# via -r demo/llama_code_editor/requirements.in
ffmpy==0.4.0
# via gradio
filelock==3.16.1
# via huggingface-hub
flatbuffers==24.3.25
# via onnxruntime
frozenlist==1.5.0
# via
# aiohttp
# aiosignal
fsspec==2024.10.0
# via
# gradio-client
# huggingface-hub
google-crc32c==1.6.0
# via aiortc
gradio==5.16.0
# via fastrtc
gradio-client==1.7.0
# via gradio
groq==0.18.0
# via -r demo/llama_code_editor/requirements.in
h11==0.14.0
# via
# httpcore
# uvicorn
httpcore==1.0.7
# via httpx
httpx==0.27.2
# via
# gradio
# gradio-client
# groq
# openai
# safehttpx
huggingface-hub==0.28.1
# via
# gradio
# gradio-client
humanfriendly==10.0
# via coloredlogs
idna==3.10
# via
# anyio
# httpx
# requests
# yarl
ifaddr==0.2.0
# via aioice
jinja2==3.1.4
# via gradio
jiter==0.7.1
# via openai
joblib==1.4.2
# via
# librosa
# scikit-learn
lazy-loader==0.4
# via librosa
librosa==0.10.2.post1
# via fastrtc
llvmlite==0.43.0
# via numba
markdown-it-py==3.0.0
# via rich
markupsafe==2.1.5
# via
# gradio
# jinja2
mdurl==0.1.2
# via markdown-it-py
mpmath==1.3.0
# via sympy
msgpack==1.1.0
# via librosa
multidict==6.1.0
# via
# aiohttp
# yarl
numba==0.60.0
# via librosa
numpy==2.0.2
# via
# gradio
# librosa
# numba
# onnxruntime
# pandas
# scikit-learn
# scipy
# soxr
onnxruntime==1.20.1
# via fastrtc
openai==1.54.4
# via -r demo/llama_code_editor/requirements.in
orjson==3.10.11
# via gradio
packaging==24.2
# via
# gradio
# gradio-client
# huggingface-hub
# lazy-loader
# onnxruntime
# pooch
pandas==2.2.3
# via gradio
pillow==11.0.0
# via gradio
platformdirs==4.3.6
# via pooch
pooch==1.8.2
# via librosa
propcache==0.2.1
# via
# aiohttp
# yarl
protobuf==5.28.3
# via onnxruntime
pycparser==2.22
# via cffi
pydantic==2.9.2
# via
# fastapi
# gradio
# groq
# openai
pydantic-core==2.23.4
# via pydantic
pydub==0.25.1
# via gradio
pyee==12.1.1
# via aiortc
pygments==2.18.0
# via rich
pyjwt==2.10.1
# via twilio
pylibsrtp==0.10.0
# via aiortc
pyopenssl==24.2.1
# via aiortc
python-dateutil==2.9.0.post0
# via pandas
python-dotenv==1.0.1
# via -r demo/llama_code_editor/requirements.in
python-multipart==0.0.20
# via gradio
pytz==2024.2
# via pandas
pyyaml==6.0.2
# via
# gradio
# huggingface-hub
requests==2.32.3
# via
# huggingface-hub
# pooch
# twilio
rich==13.9.4
# via typer
ruff==0.9.6
# via gradio
safehttpx==0.1.6
# via gradio
scikit-learn==1.5.2
# via librosa
scipy==1.14.1
# via
# librosa
# scikit-learn
semantic-version==2.10.0
# via gradio
shellingham==1.5.4
# via typer
six==1.16.0
# via python-dateutil
sniffio==1.3.1
# via
# anyio
# groq
# httpx
# openai
soundfile==0.12.1
# via librosa
soxr==0.5.0.post1
# via librosa
starlette==0.41.3
# via
# fastapi
# gradio
sympy==1.13.3
# via onnxruntime
threadpoolctl==3.5.0
# via scikit-learn
tomlkit==0.12.0
# via gradio
tqdm==4.67.0
# via
# huggingface-hub
# openai
twilio==9.4.5
# via -r demo/llama_code_editor/requirements.in
typer==0.13.1
# via gradio
typing-extensions==4.12.2
# via
# fastapi
# gradio
# gradio-client
# groq
# huggingface-hub
# librosa
# openai
# pydantic
# pydantic-core
# pyee
# typer
tzdata==2024.2
# via pandas
urllib3==2.2.3
# via requests
uvicorn==0.32.0
# via gradio
websockets==12.0
# via gradio-client
yarl==1.18.3
# via aiohttp

75
demo/llama_code_editor/ui.py Normal file
View File

@@ -0,0 +1,75 @@
from pathlib import Path
import gradio as gr
from dotenv import load_dotenv
from fastrtc import WebRTC, get_twilio_turn_credentials
from gradio.utils import get_space
try:
from demo.llama_code_editor.handler import (
CodeHandler,
display_in_sandbox,
system_prompt,
)
except (ImportError, ModuleNotFoundError):
from handler import CodeHandler, display_in_sandbox, system_prompt
load_dotenv()
path = Path(__file__).parent / "assets"
with gr.Blocks(css=".code-component {max-height: 500px !important}") as demo:
history = gr.State([{"role": "system", "content": system_prompt}])
with gr.Row():
with gr.Column(scale=1):
gr.HTML(
"""
<h1 style='text-align: center'>
Llama Code Editor
</h1>
<h2 style='text-align: center'>
Powered by SambaNova and Gradio-WebRTC ⚡️
</h2>
<p style='text-align: center'>
Create and edit single-file HTML applications with just your voice!
</p>
<p style='text-align: center'>
Each conversation is limited to 90 seconds. Once the time limit is up you can rejoin the conversation.
</p>
"""
)
webrtc = WebRTC(
rtc_configuration=get_twilio_turn_credentials()
if get_space()
else None,
mode="send",
modality="audio",
)
with gr.Column(scale=10):
with gr.Tabs():
with gr.Tab("Sandbox"):
sandbox = gr.HTML(value=open(path / "sandbox.html").read())
with gr.Tab("Code"):
code = gr.Code(
language="html",
max_lines=50,
interactive=False,
elem_classes="code-component",
)
with gr.Tab("Chat"):
cb = gr.Chatbot(type="messages")
webrtc.stream(
CodeHandler,
inputs=[webrtc, history, code],
outputs=[webrtc],
time_limit=90 if get_space() else None,
concurrency_limit=10 if get_space() else None,
)
webrtc.on_additional_outputs(
lambda history, code: (history, code, history), outputs=[history, code, cb]
)
code.change(display_in_sandbox, code, sandbox, queue=False)
if __name__ == "__main__":
demo.launch()

15
demo/llm_voice_chat/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: LLM Voice Chat
emoji: 💻
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to an LLM with ElevenLabs
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GROQ_API_KEY, secret|ELEVENLABS_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

15
demo/llm_voice_chat/README_gradio.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: LLM Voice Chat (Gradio)
emoji: 💻
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: LLM Voice by ElevenLabs (Gradio)
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GROQ_API_KEY, secret|ELEVENLABS_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

101
demo/llm_voice_chat/app.py Normal file
View File

@@ -0,0 +1,101 @@
import os
import time
import gradio as gr
import numpy as np
from dotenv import load_dotenv
from elevenlabs import ElevenLabs
from fastapi import FastAPI
from fastrtc import (
AdditionalOutputs,
ReplyOnPause,
Stream,
WebRTCError,
get_stt_model,
get_twilio_turn_credentials,
)
from gradio.utils import get_space
from groq import Groq
from numpy.typing import NDArray
load_dotenv()
groq_client = Groq()
tts_client = ElevenLabs(api_key=os.getenv("ELEVENLABS_API_KEY"))
stt_model = get_stt_model()
# See "Talk to Claude" in Cookbook for an example of how to keep
# track of the chat history.
def response(
audio: tuple[int, NDArray[np.int16 | np.float32]],
chatbot: list[dict] | None = None,
):
try:
chatbot = chatbot or []
messages = [{"role": d["role"], "content": d["content"]} for d in chatbot]
start = time.time()
text = stt_model.stt(audio)
print("transcription", time.time() - start)
print("prompt", text)
chatbot.append({"role": "user", "content": text})
yield AdditionalOutputs(chatbot)
messages.append({"role": "user", "content": text})
response_text = (
groq_client.chat.completions.create(
model="llama-3.1-8b-instant",
max_tokens=512,
messages=messages, # type: ignore
)
.choices[0]
.message.content
)
chatbot.append({"role": "assistant", "content": response_text})
for chunk in tts_client.text_to_speech.convert_as_stream(
text=response_text, # type: ignore
voice_id="JBFqnCBsd6RMkjVDRZzb",
model_id="eleven_multilingual_v2",
output_format="pcm_24000",
):
audio_array = np.frombuffer(chunk, dtype=np.int16).reshape(1, -1)
yield (24000, audio_array)
yield AdditionalOutputs(chatbot)
except Exception:
import traceback
traceback.print_exc()
raise WebRTCError(traceback.format_exc())
chatbot = gr.Chatbot(type="messages")
stream = Stream(
modality="audio",
mode="send-receive",
handler=ReplyOnPause(response, input_sample_rate=16000),
additional_outputs_handler=lambda a, b: b,
additional_inputs=[chatbot],
additional_outputs=[chatbot],
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
ui_args={"title": "LLM Voice Chat (Powered by Groq, ElevenLabs, and WebRTC ⚡️)"},
)
# Mount the STREAM UI to the FastAPI app
# Because I don't want to build the UI manually
app = FastAPI()
app = gr.mount_gradio_app(app, stream.ui, path="/")
if __name__ == "__main__":
import os
os.environ["GRADIO_SSR_MODE"] = "false"
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
stream.ui.launch(server_port=7860)

6
demo/llm_voice_chat/requirements.txt Normal file
View File

@@ -0,0 +1,6 @@
fastrtc[stopword]
python-dotenv
openai
twilio
groq
elevenlabs

15
demo/object_detection/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Object Detection
emoji: 📸
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Use YOLOv10 to detect objects in real-time
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

83
demo/object_detection/app.py Normal file
View File

@@ -0,0 +1,83 @@
import json
from pathlib import Path
import cv2
import gradio as gr
from fastapi import FastAPI
from fastapi.responses import HTMLResponse
from fastrtc import Stream, WebRTCError, get_twilio_turn_credentials
from gradio.utils import get_space
from huggingface_hub import hf_hub_download
from pydantic import BaseModel, Field
try:
from demo.object_detection.inference import YOLOv10
except (ImportError, ModuleNotFoundError):
from inference import YOLOv10
cur_dir = Path(__file__).parent
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
def detection(image, conf_threshold=0.3):
try:
image = cv2.resize(image, (model.input_width, model.input_height))
print("conf_threshold", conf_threshold)
new_image = model.detect_objects(image, conf_threshold)
return cv2.resize(new_image, (500, 500))
except Exception as e:
import traceback
traceback.print_exc()
raise WebRTCError(str(e))
stream = Stream(
handler=detection,
modality="video",
mode="send-receive",
additional_inputs=[gr.Slider(minimum=0, maximum=1, step=0.01, value=0.3)],
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=2 if get_space() else None,
)
app = FastAPI()
stream.mount(app)
@app.get("/")
async def _():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = open(cur_dir / "index.html").read()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content)
class InputData(BaseModel):
webrtc_id: str
conf_threshold: float = Field(ge=0, le=1)
@app.post("/input_hook")
async def _(data: InputData):
stream.set_input(data.webrtc_id, data.conf_threshold)
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

340
demo/object_detection/index.html Normal file
View File

@@ -0,0 +1,340 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Object Detection</title>
<style>
body {
font-family: system-ui, -apple-system, sans-serif;
background: linear-gradient(135deg, #2d2b52 0%, #191731 100%);
color: white;
margin: 0;
padding: 20px;
height: 100vh;
box-sizing: border-box;
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
}
.container {
width: 100%;
max-width: 800px;
text-align: center;
display: flex;
flex-direction: column;
align-items: center;
}
.video-container {
width: 100%;
max-width: 500px;
aspect-ratio: 1/1;
background: rgba(255, 255, 255, 0.1);
border-radius: 12px;
overflow: hidden;
box-shadow: 0 8px 32px rgba(0, 0, 0, 0.2);
margin: 10px 0;
}
#video-output {
width: 100%;
height: 100%;
object-fit: cover;
}
button {
background: white;
color: #2d2b52;
border: none;
padding: 12px 32px;
border-radius: 24px;
font-size: 16px;
font-weight: 600;
cursor: pointer;
transition: all 0.3s ease;
box-shadow: 0 4px 12px rgba(0, 0, 0, 0.1);
}
button:hover {
transform: translateY(-2px);
box-shadow: 0 6px 16px rgba(0, 0, 0, 0.2);
}
h1 {
font-size: 2.5em;
margin-bottom: 0.3em;
}
p {
color: rgba(255, 255, 255, 0.8);
margin-bottom: 1em;
}
.controls {
display: flex;
flex-direction: column;
gap: 12px;
align-items: center;
margin-top: 10px;
}
.slider-container {
width: 100%;
max-width: 300px;
display: flex;
flex-direction: column;
gap: 8px;
}
.slider-container label {
color: rgba(255, 255, 255, 0.8);
font-size: 14px;
}
input[type="range"] {
width: 100%;
height: 6px;
-webkit-appearance: none;
background: rgba(255, 255, 255, 0.1);
border-radius: 3px;
outline: none;
}
input[type="range"]::-webkit-slider-thumb {
-webkit-appearance: none;
width: 18px;
height: 18px;
background: white;
border-radius: 50%;
cursor: pointer;
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div class="container">
<h1>Real-time Object Detection</h1>
<p>Using YOLOv10 to detect objects in your webcam feed</p>
<div class="video-container">
<video id="video-output" autoplay playsinline></video>
</div>
<div class="controls">
<div class="slider-container">
<label>Confidence Threshold: <span id="conf-value">0.3</span></label>
<input type="range" id="conf-threshold" min="0" max="1" step="0.01" value="0.3">
</div>
<button id="start-button">Start</button>
</div>
</div>
<script>
let peerConnection;
let webrtc_id;
const startButton = document.getElementById('start-button');
const videoOutput = document.getElementById('video-output');
const confThreshold = document.getElementById('conf-threshold');
const confValue = document.getElementById('conf-value');
// Update confidence value display
confThreshold.addEventListener('input', (e) => {
confValue.textContent = e.target.value;
if (peerConnection) {
updateConfThreshold(e.target.value);
}
});
function updateConfThreshold(value) {
fetch('/input_hook', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({
webrtc_id: webrtc_id,
conf_threshold: parseFloat(value)
})
});
}
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.className = 'toast error';
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
async function setupWebRTC() {
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({
video: true
});
stream.getTracks().forEach(track => {
peerConnection.addTrack(track, stream);
});
peerConnection.addEventListener('track', (evt) => {
if (videoOutput && videoOutput.srcObject !== evt.streams[0]) {
videoOutput.srcObject = evt.streams[0];
}
});
const dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = (event) => {
const eventJson = JSON.parse(event.data);
if (eventJson.type === "error") {
showError(eventJson.message);
} else if (eventJson.type === "send_input") {
updateConfThreshold(confThreshold.value);
}
};
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
webrtc_id = Math.random().toString(36).substring(7);
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
startButton.textContent = 'Start';
return;
}
await peerConnection.setRemoteDescription(serverResponse);
// Send initial confidence threshold
updateConfThreshold(confThreshold.value);
peerConnection.addEventListener('connectionstatechange', () => {
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
});
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
startButton.textContent = 'Start';
}
}
function stop() {
if (peerConnection) {
if (peerConnection.getTransceivers) {
peerConnection.getTransceivers().forEach(transceiver => {
if (transceiver.stop) {
transceiver.stop();
}
});
}
if (peerConnection.getSenders) {
peerConnection.getSenders().forEach(sender => {
if (sender.track && sender.track.stop) sender.track.stop();
});
}
setTimeout(() => {
peerConnection.close();
}, 500);
}
videoOutput.srcObject = null;
}
startButton.addEventListener('click', () => {
if (startButton.textContent === 'Start') {
setupWebRTC();
startButton.textContent = 'Stop';
} else {
stop();
startButton.textContent = 'Start';
}
});
</script>
</body>
</html>

10
demo/inference.py → demo/object_detection/inference.py
View File

@@ -3,7 +3,11 @@ import time
import cv2
import numpy as np
import onnxruntime
from utils import draw_detections
try:
from demo.object_detection.utils import draw_detections
except (ImportError, ModuleNotFoundError):
from utils import draw_detections
class YOLOv10:
@@ -51,7 +55,7 @@ class YOLOv10:
self.output_names, {self.input_names[0]: input_tensor}
)
print(f"Inference time: {(time.perf_counter() - start)*1000:.2f} ms")
print(f"Inference time: {(time.perf_counter() - start) * 1000:.2f} ms")
(
boxes,
scores,
@@ -71,7 +75,7 @@ class YOLOv10:
return [], [], []
# Get the class with the highest confidence
class_ids = np.argmax(predictions[:, 4:], axis=1)
class_ids = predictions[:, 5].astype(int)
# Get bounding boxes for each object
boxes = self.extract_boxes(predictions)

4
demo/object_detection/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc
opencv-python
twilio
onnxruntime-gpu

6
demo/utils.py → demo/object_detection/utils.py
View File

@@ -170,11 +170,11 @@ def draw_detections(image, boxes, scores, class_ids, mask_alpha=0.3):
for class_id, box, score in zip(class_ids, boxes, scores):
color = colors[class_id]
draw_box(det_img, box, color)
draw_box(det_img, box, color) # type: ignore
label = class_names[class_id]
caption = f"{label} {int(score * 100)}%"
draw_text(det_img, caption, box, color, font_size, text_thickness)
draw_text(det_img, caption, box, color, font_size, text_thickness) # type: ignore
return det_img
@@ -232,6 +232,6 @@ def draw_masks(
x1, y1, x2, y2 = box.astype(int)
# Draw fill rectangle in mask image
cv2.rectangle(mask_img, (x1, y1), (x2, y2), color, -1)
cv2.rectangle(mask_img, (x1, y1), (x2, y2), color, -1) # type: ignore
return cv2.addWeighted(mask_img, mask_alpha, image, 1 - mask_alpha, 0)

74
demo/old_app.py
View File

@@ -1,74 +0,0 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from huggingface_hub import hf_hub_download
from inference import YOLOv10
from twilio.rest import Client
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def detection(frame, conf_threshold=0.3):
frame = cv2.flip(frame, 0)
return cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks(css=css) as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
</h1>
"""
)
gr.HTML(
"""
<h3 style='text-align: center'>
<a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
</h3>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
image = WebRTC(label="Stream", rtc_configuration=rtc_configuration)
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
number = gr.Number()
image.stream(
fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=10
)
image.on_additional_outputs(lambda n: n, outputs=[number])
if __name__ == "__main__":
demo.launch()

16
demo/phonic_chat/README.md Normal file
View File

@@ -0,0 +1,16 @@
---
title: Phonic AI Chat
emoji: 🎙️
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to Phonic AI's speech-to-speech model
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|PHONIC_API_KEY]
python_version: 3.11
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

134
demo/phonic_chat/app.py Normal file
View File

@@ -0,0 +1,134 @@
import subprocess
subprocess.run(["pip", "install", "fastrtc==0.0.3.post7"])
import asyncio
import base64
import os
import gradio as gr
from gradio.utils import get_space
import numpy as np
from dotenv import load_dotenv
from fastrtc import (
AdditionalOutputs,
AsyncStreamHandler,
Stream,
get_twilio_turn_credentials,
WebRTCError,
audio_to_float32,
)
from fastapi import FastAPI
from phonic.client import PhonicSTSClient, get_voices
load_dotenv()
STS_URI = "wss://api.phonic.co/v1/sts/ws"
API_KEY = os.environ["PHONIC_API_KEY"]
SAMPLE_RATE = 44_100
voices = get_voices(API_KEY)
voice_ids = [voice["id"] for voice in voices]
class PhonicHandler(AsyncStreamHandler):
def __init__(self):
super().__init__(input_sample_rate=SAMPLE_RATE, output_sample_rate=SAMPLE_RATE)
self.output_queue = asyncio.Queue()
self.client = None
def copy(self) -> AsyncStreamHandler:
return PhonicHandler()
async def start_up(self):
await self.wait_for_args()
voice_id = self.latest_args[1]
try:
async with PhonicSTSClient(STS_URI, API_KEY) as client:
self.client = client
sts_stream = client.sts( # type: ignore
input_format="pcm_44100",
output_format="pcm_44100",
system_prompt="You are a helpful voice assistant. Respond conversationally.",
# welcome_message="Hello! I'm your voice assistant. How can I help you today?",
voice_id=voice_id,
)
async for message in sts_stream:
message_type = message.get("type")
if message_type == "audio_chunk":
audio_b64 = message["audio"]
audio_bytes = base64.b64decode(audio_b64)
await self.output_queue.put(
(SAMPLE_RATE, np.frombuffer(audio_bytes, dtype=np.int16))
)
if text := message.get("text"):
msg = {"role": "assistant", "content": text}
await self.output_queue.put(AdditionalOutputs(msg))
elif message_type == "input_text":
msg = {"role": "user", "content": message["text"]}
await self.output_queue.put(AdditionalOutputs(msg))
except Exception as e:
raise WebRTCError(f"Error starting up: {e}")
async def emit(self):
try:
return await self.output_queue.get()
except Exception as e:
raise WebRTCError(f"Error emitting: {e}")
async def receive(self, frame: tuple[int, np.ndarray]) -> None:
try:
if not self.client:
return
audio_float32 = audio_to_float32(frame)
await self.client.send_audio(audio_float32) # type: ignore
except Exception as e:
raise WebRTCError(f"Error sending audio: {e}")
async def shutdown(self):
if self.client:
await self.client._websocket.close()
return super().shutdown()
def add_to_chatbot(state, chatbot, message):
state.append(message)
return state, gr.skip()
state = gr.State(value=[])
chatbot = gr.Chatbot(type="messages", value=[])
stream = Stream(
handler=PhonicHandler(),
mode="send-receive",
modality="audio",
additional_inputs=[
gr.Dropdown(
choices=voice_ids,
value="katherine",
label="Voice",
info="Select a voice from the dropdown",
)
],
additional_outputs=[state, chatbot],
additional_outputs_handler=add_to_chatbot,
ui_args={
"title": "Phonic Chat (Powered by FastRTC ⚡️)",
},
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
)
with stream.ui:
state.change(lambda s: s, inputs=state, outputs=chatbot)
app = FastAPI()
stream.mount(app)
if __name__ == "__main__":
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
stream.ui.launch(server_port=7860)

74
demo/phonic_chat/requirements.txt Normal file
View File

@@ -0,0 +1,74 @@
# This file was autogenerated by uv via the following command:
# uv pip compile requirements.in -o requirements.txt
aiohappyeyeballs==2.4.6
# via aiohttp
aiohttp==3.11.12
# via
# aiohttp-retry
# twilio
aiohttp-retry==2.9.1
# via twilio
aiosignal==1.3.2
# via aiohttp
attrs==25.1.0
# via aiohttp
certifi==2025.1.31
# via requests
cffi==1.17.1
# via sounddevice
charset-normalizer==3.4.1
# via requests
fastrtc==0.0.1
# via -r requirements.in
frozenlist==1.5.0
# via
# aiohttp
# aiosignal
idna==3.10
# via
# requests
# yarl
isort==6.0.0
# via phonic-python
loguru==0.7.3
# via phonic-python
multidict==6.1.0
# via
# aiohttp
# yarl
numpy==2.2.3
# via
# phonic-python
# scipy
phonic-python==0.1.3
# via -r requirements.in
propcache==0.3.0
# via
# aiohttp
# yarl
pycparser==2.22
# via cffi
pyjwt==2.10.1
# via twilio
python-dotenv==1.0.1
# via
# -r requirements.in
# phonic-python
requests==2.32.3
# via
# phonic-python
# twilio
scipy==1.15.2
# via phonic-python
sounddevice==0.5.1
# via phonic-python
twilio==9.4.6
# via -r requirements.in
typing-extensions==4.12.2
# via phonic-python
urllib3==2.3.0
# via requests
websockets==15.0
# via phonic-python
yarl==1.18.3
# via aiohttp

6
demo/requirements.txt
View File

@@ -1,6 +0,0 @@
safetensors==0.4.3
opencv-python
twilio
https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio-5.0.0b3-py3-none-any.whl
https://huggingface.co/datasets/freddyaboulton/bucket/resolve/main/gradio_webrtc-0.0.1-py3-none-any.whl
onnxruntime-gpu

321
demo/space.py
View File

@@ -1,321 +0,0 @@
import os
import gradio as gr
_docs = {
"WebRTC": {
"description": "Stream audio/video with WebRTC",
"members": {
"__init__": {
"rtc_configuration": {
"type": "dict[str, Any] | None",
"default": "None",
"description": "The configration dictionary to pass to the RTCPeerConnection constructor. If None, the default configuration is used.",
},
"height": {
"type": "int | str | None",
"default": "None",
"description": "The height of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"width": {
"type": "int | str | None",
"default": "None",
"description": "The width of the component, specified in pixels if a number is passed, or in CSS units if a string is passed. This has no effect on the preprocessed video file, but will affect the displayed video.",
},
"label": {
"type": "str | None",
"default": "None",
"description": "the label for this component. Appears above the component and is also used as the header if there are a table of examples for this component. If None and used in a `gr.Interface`, the label will be the name of the parameter this component is assigned to.",
},
"show_label": {
"type": "bool | None",
"default": "None",
"description": "if True, will display label.",
},
"container": {
"type": "bool",
"default": "True",
"description": "if True, will place the component in a container - providing some extra padding around the border.",
},
"scale": {
"type": "int | None",
"default": "None",
"description": "relative size compared to adjacent Components. For example if Components A and B are in a Row, and A has scale=2, and B has scale=1, A will be twice as wide as B. Should be an integer. scale applies in Rows, and to top-level Components in Blocks where fill_height=True.",
},
"min_width": {
"type": "int",
"default": "160",
"description": "minimum pixel width, will wrap if not sufficient screen space to satisfy this value. If a certain scale value results in this Component being narrower than min_width, the min_width parameter will be respected first.",
},
"interactive": {
"type": "bool | None",
"default": "None",
"description": "if True, will allow users to upload a video; if False, can only be used to display videos. If not provided, this is inferred based on whether the component is used as an input or output.",
},
"visible": {
"type": "bool",
"default": "True",
"description": "if False, component will be hidden.",
},
"elem_id": {
"type": "str | None",
"default": "None",
"description": "an optional string that is assigned as the id of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"elem_classes": {
"type": "list[str] | str | None",
"default": "None",
"description": "an optional list of strings that are assigned as the classes of this component in the HTML DOM. Can be used for targeting CSS styles.",
},
"render": {
"type": "bool",
"default": "True",
"description": "if False, component will not render be rendered in the Blocks context. Should be used if the intention is to assign event listeners now but render the component later.",
},
"key": {
"type": "int | str | None",
"default": "None",
"description": "if assigned, will be used to assume identity across a re-render. Components that have the same key across a re-render will have their value preserved.",
},
"mirror_webcam": {
"type": "bool",
"default": "True",
"description": "if True webcam will be mirrored. Default is True.",
},
},
"events": {"tick": {"type": None, "default": None, "description": ""}},
},
"__meta__": {"additional_interfaces": {}, "user_fn_refs": {"WebRTC": []}},
}
}
abs_path = os.path.join(os.path.dirname(__file__), "css.css")
with gr.Blocks(
css_paths=abs_path,
theme=gr.themes.Default(
font_mono=[
gr.themes.GoogleFont("Inconsolata"),
"monospace",
],
),
) as demo:
gr.Markdown(
"""
<h1 style='text-align: center; margin-bottom: 1rem'> Gradio WebRTC ⚡️ </h1>
<div style="display: flex; flex-direction: row; justify-content: center">
<img style="display: block; padding-right: 5px; height: 20px;" alt="Static Badge" src="https://img.shields.io/badge/version%20-%200.0.5%20-%20orange">
<a href="https://github.com/freddyaboulton/gradio-webrtc" target="_blank"><img alt="Static Badge" src="https://img.shields.io/badge/github-white?logo=github&logoColor=black"></a>
</div>
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
## Installation
```bash
pip install gradio_webrtc
```
## Examples:
1. [Object Detection from Webcam with YOLOv10](https://huggingface.co/spaces/freddyaboulton/webrtc-yolov10n) 📷
2. [Streaming Object Detection from Video with RT-DETR](https://huggingface.co/spaces/freddyaboulton/rt-detr-object-detection-webrtc) 🎥
3. [Text-to-Speech](https://huggingface.co/spaces/freddyaboulton/parler-tts-streaming-webrtc) 🗣️
## Usage
The WebRTC component supports the following three use cases:
1. Streaming video from the user webcam to the server and back
2. Streaming Video from the server to the client
3. Streaming Audio from the server to the client
Streaming Audio from client to the server and back (conversational AI) is not supported yet.
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
def detection(image, conf_threshold=0.3):
... your detection code here ...
with gr.Blocks() as demo:
image = WebRTC(label="Stream", mode="send-receive", modality="video")
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
image.stream(
fn=detection,
inputs=[image, conf_threshold],
outputs=[image], time_limit=10
)
if __name__ == "__main__":
demo.launch()
```
* Set the `mode` parameter to `send-receive` and `modality` to "video".
* The `stream` event's `fn` parameter is a function that receives the next frame from the webcam
as a **numpy array** and returns the processed frame also as a **numpy array**.
* Numpy arrays are in (height, width, 3) format where the color channels are in RGB format.
* The `inputs` parameter should be a list where the first element is the WebRTC component. The only output allowed is the WebRTC component.
* The `time_limit` parameter is the maximum time in seconds the video stream will run. If the time limit is reached, the video stream will stop.
## Streaming Video from the User Webcam to the Server and Back
```python
import gradio as gr
from gradio_webrtc import WebRTC
import cv2
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
output_video = WebRTC(label="Video Stream", mode="receive", modality="video")
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video],
trigger=button.click
)
if __name__ == "__main__":
demo.launch()
```
* Set the "mode" parameter to "receive" and "modality" to "video".
* The `stream` event's `fn` parameter is a generator function that yields the next frame from the video as a **numpy array**.
* The only output allowed is the WebRTC component.
* The `trigger` parameter the gradio event that will trigger the webrtc connection. In this case, the button click event.
## Streaming Audio from the Server to the Client
```python
import gradio as gr
from pydub import AudioSegment
def generation(num_steps):
for _ in range(num_steps):
segment = AudioSegment.from_file("/Users/freddy/sources/gradio/demo/audio_debugger/cantina.wav")
yield (segment.frame_rate, np.array(segment.get_array_of_samples()).reshape(1, -1))
with gr.Blocks() as demo:
audio = WebRTC(label="Stream", mode="receive", modality="audio")
num_steps = gr.Slider(
label="Number of Steps",
minimum=1,
maximum=10,
step=1,
value=5,
)
button = gr.Button("Generate")
audio.stream(
fn=generation, inputs=[num_steps], outputs=[audio],
trigger=button.click
)
```
* Set the "mode" parameter to "receive" and "modality" to "audio".
* The `stream` event's `fn` parameter is a generator function that yields the next audio segment as a tuple of (frame_rate, audio_samples).
* The numpy array should be of shape (1, num_samples).
* The `outputs` parameter should be a list with the WebRTC component as the only element.
## Deployment
When deploying in a cloud environment (like Hugging Face Spaces, EC2, etc), you need to set up a TURN server to relay the WebRTC traffic.
The easiest way to do this is to use a service like Twilio.
```python
from twilio.rest import Client
import os
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
with gr.Blocks() as demo:
...
rtc = WebRTC(rtc_configuration=rtc_configuration, ...)
...
```
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.Markdown(
"""
##
""",
elem_classes=["md-custom"],
header_links=True,
)
gr.ParamViewer(value=_docs["WebRTC"]["members"]["__init__"], linkify=[])
demo.load(
None,
js=r"""function() {
const refs = {};
const user_fn_refs = {
WebRTC: [], };
requestAnimationFrame(() => {
Object.entries(user_fn_refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}-user-fn`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
Object.entries(refs).forEach(([key, refs]) => {
if (refs.length > 0) {
const el = document.querySelector(`.${key}`);
if (!el) return;
refs.forEach(ref => {
el.innerHTML = el.innerHTML.replace(
new RegExp("\\b"+ref+"\\b", "g"),
`<a href="#h-${ref.toLowerCase()}">${ref}</a>`
);
})
}
})
})
}
""",
)
demo.launch()

53
demo/stream_whisper.py
View File

@@ -1,53 +0,0 @@
import tempfile
import gradio as gr
import numpy as np
from gradio_webrtc import AdditionalOutputs, ReplyOnPause, WebRTC
from openai import OpenAI
from pydub import AudioSegment
from dotenv import load_dotenv
load_dotenv()
client = OpenAI()
def transcribe(audio: tuple[int, np.ndarray], transcript: list[dict]):
print("audio", audio)
segment = AudioSegment(
audio[1].tobytes(),
frame_rate=audio[0],
sample_width=audio[1].dtype.itemsize,
channels=1,
)
transcript.append({"role": "user", "content": gr.Audio((audio[0], audio[1].squeeze()))})
with tempfile.NamedTemporaryFile(suffix=".mp3") as temp_audio:
segment.export(temp_audio.name, format="mp3")
next_chunk = client.audio.transcriptions.create(
model="whisper-1", file=open(temp_audio.name, "rb")
).text
transcript.append({"role": "assistant", "content": next_chunk})
yield AdditionalOutputs(transcript)
with gr.Blocks() as demo:
with gr.Row():
with gr.Column():
audio = WebRTC(
label="Stream",
mode="send",
modality="audio",
)
with gr.Column():
transcript = gr.Chatbot(label="transcript", type="messages")
audio.stream(ReplyOnPause(transcribe), inputs=[audio, transcript], outputs=[audio],
time_limit=30)
audio.on_additional_outputs(lambda s: s, outputs=transcript)
if __name__ == "__main__":
demo.launch()

15
demo/talk_to_claude/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to Claude
emoji: 👨‍🦰
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to Anthropic's Claude
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GROQ_API_KEY, secret|ANTHROPIC_API_KEY, secret|ELEVENLABS_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

140
demo/talk_to_claude/app.py Normal file
View File

@@ -0,0 +1,140 @@
import json
import os
import time
from pathlib import Path
import anthropic
import gradio as gr
import numpy as np
from dotenv import load_dotenv
from elevenlabs import ElevenLabs
from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse
from fastrtc import (
AdditionalOutputs,
ReplyOnPause,
Stream,
WebRTCError,
get_tts_model,
get_twilio_turn_credentials,
)
from fastrtc.utils import audio_to_bytes
from gradio.utils import get_space
from groq import Groq
from pydantic import BaseModel
load_dotenv()
groq_client = Groq()
claude_client = anthropic.Anthropic()
tts_client = ElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"])
curr_dir = Path(__file__).parent
tts_model = get_tts_model()
def response(
audio: tuple[int, np.ndarray],
chatbot: list[dict] | None = None,
):
try:
chatbot = chatbot or []
messages = [{"role": d["role"], "content": d["content"]} for d in chatbot]
prompt = groq_client.audio.transcriptions.create(
file=("audio-file.mp3", audio_to_bytes(audio)),
model="whisper-large-v3-turbo",
response_format="verbose_json",
).text
print("prompt", prompt)
chatbot.append({"role": "user", "content": prompt})
yield AdditionalOutputs(chatbot)
messages.append({"role": "user", "content": prompt})
response = claude_client.messages.create(
model="claude-3-5-haiku-20241022",
max_tokens=512,
messages=messages, # type: ignore
)
response_text = " ".join(
block.text # type: ignore
for block in response.content
if getattr(block, "type", None) == "text"
)
chatbot.append({"role": "assistant", "content": response_text})
start = time.time()
print("starting tts", start)
for i, chunk in enumerate(tts_model.stream_tts_sync(response_text)):
print("chunk", i, time.time() - start)
yield chunk
print("finished tts", time.time() - start)
yield AdditionalOutputs(chatbot)
except Exception as e:
raise WebRTCError(str(e))
chatbot = gr.Chatbot(type="messages")
stream = Stream(
modality="audio",
mode="send-receive",
handler=ReplyOnPause(response),
additional_outputs_handler=lambda a, b: b,
additional_inputs=[chatbot],
additional_outputs=[chatbot],
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
)
class Message(BaseModel):
role: str
content: str
class InputData(BaseModel):
webrtc_id: str
chatbot: list[Message]
app = FastAPI()
stream.mount(app)
@app.get("/")
async def _():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (curr_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content, status_code=200)
@app.post("/input_hook")
async def _(body: InputData):
stream.set_input(body.webrtc_id, body.model_dump()["chatbot"])
return {"status": "ok"}
@app.get("/outputs")
def _(webrtc_id: str):
async def output_stream():
async for output in stream.output_stream(webrtc_id):
chatbot = output.args[0]
yield f"event: output\ndata: {json.dumps(chatbot[-1])}\n\n"
return StreamingResponse(output_stream(), media_type="text/event-stream")
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860, server_name="0.0.0.0")
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

546
demo/talk_to_claude/index.html Normal file
View File

@@ -0,0 +1,546 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>RetroChat Audio</title>
<style>
body {
font-family: monospace;
background-color: #1a1a1a;
color: #00ff00;
margin: 0;
padding: 20px;
height: 100vh;
box-sizing: border-box;
}
.container {
display: flex;
flex-direction: column;
gap: 20px;
height: calc(100% - 100px);
margin-bottom: 20px;
}
.chat-container {
border: 2px solid #00ff00;
padding: 20px;
display: flex;
flex-direction: column;
flex-grow: 1;
box-sizing: border-box;
}
.controls-container {
border: 2px solid #00ff00;
padding: 20px;
display: flex;
align-items: center;
gap: 20px;
height: 128px;
box-sizing: border-box;
}
.visualization-container {
flex-grow: 1;
display: flex;
align-items: center;
}
.box-container {
display: flex;
justify-content: space-between;
height: 64px;
width: 100%;
}
.box {
height: 100%;
width: 8px;
background: #00ff00;
border-radius: 8px;
transition: transform 0.05s ease;
}
.chat-messages {
flex-grow: 1;
overflow-y: auto;
margin-bottom: 20px;
padding: 10px;
border: 1px solid #00ff00;
}
.message {
margin-bottom: 10px;
padding: 8px;
border-radius: 4px;
}
.message.user {
background-color: #003300;
}
.message.assistant {
background-color: #002200;
}
button {
height: 64px;
min-width: 120px;
background-color: #000;
color: #00ff00;
border: 2px solid #00ff00;
padding: 10px 20px;
font-family: monospace;
font-size: 16px;
cursor: pointer;
transition: all 0.3s;
}
button:hover {
border-width: 3px;
}
#audio-output {
display: none;
}
/* Retro CRT effect */
.crt-overlay {
position: absolute;
top: 0;
left: 0;
width: 100%;
height: 100%;
background: repeating-linear-gradient(0deg,
rgba(0, 255, 0, 0.03),
rgba(0, 255, 0, 0.03) 1px,
transparent 1px,
transparent 2px);
pointer-events: none;
}
/* Add these new styles */
.icon-with-spinner {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.spinner {
width: 20px;
height: 20px;
border: 2px solid #00ff00;
border-top-color: transparent;
border-radius: 50%;
animation: spin 1s linear infinite;
flex-shrink: 0;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
.pulse-container {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.pulse-circle {
width: 20px;
height: 20px;
border-radius: 50%;
background-color: #00ff00;
opacity: 0.2;
flex-shrink: 0;
transform: translateX(-0%) scale(var(--audio-level, 1));
transition: transform 0.1s ease;
}
/* Add styles for typing indicator */
.typing-indicator {
padding: 8px;
background-color: #002200;
border-radius: 4px;
margin-bottom: 10px;
display: none;
}
.dots {
display: inline-flex;
gap: 4px;
}
.dot {
width: 8px;
height: 8px;
background-color: #00ff00;
border-radius: 50%;
animation: pulse 1.5s infinite;
opacity: 0.5;
}
.dot:nth-child(2) {
animation-delay: 0.5s;
}
.dot:nth-child(3) {
animation-delay: 1s;
}
@keyframes pulse {
0%,
100% {
opacity: 0.5;
transform: scale(1);
}
50% {
opacity: 1;
transform: scale(1.2);
}
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div class="container">
<div class="chat-container">
<div class="chat-messages" id="chat-messages"></div>
<!-- Move typing indicator outside the chat messages -->
<div class="typing-indicator" id="typing-indicator">
<div class="dots">
<div class="dot"></div>
<div class="dot"></div>
<div class="dot"></div>
</div>
</div>
</div>
<div class="controls-container">
<div class="visualization-container">
<div class="box-container">
<!-- Boxes will be dynamically added here -->
</div>
</div>
<button id="start-button">Start</button>
</div>
</div>
<audio id="audio-output"></audio>
<script>
let audioContext;
let analyser_input, analyser_output;
let dataArray_input, dataArray_output;
let animationId_input, animationId_output;
let chatHistory = [];
let peerConnection;
let webrtc_id;
const audioOutput = document.getElementById('audio-output');
const startButton = document.getElementById('start-button');
const chatMessages = document.getElementById('chat-messages');
function updateButtonState() {
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
startButton.innerHTML = `
<div class="icon-with-spinner">
<div class="spinner"></div>
<span>Connecting...</span>
</div>
`;
} else if (peerConnection && peerConnection.connectionState === 'connected') {
startButton.innerHTML = `
<div class="pulse-container">
<div class="pulse-circle"></div>
<span>Stop</span>
</div>
`;
} else {
startButton.innerHTML = 'Start';
}
}
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.className = 'toast error';
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
async function setupWebRTC() {
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({
audio: true
});
// Set up input visualization
audioContext = new AudioContext();
analyser_input = audioContext.createAnalyser();
const inputSource = audioContext.createMediaStreamSource(stream);
inputSource.connect(analyser_input);
analyser_input.fftSize = 64;
dataArray_input = new Uint8Array(analyser_input.frequencyBinCount);
function updateAudioLevel() {
analyser_input.getByteFrequencyData(dataArray_input);
const average = Array.from(dataArray_input).reduce((a, b) => a + b, 0) / dataArray_input.length;
const audioLevel = average / 255;
const pulseCircle = document.querySelector('.pulse-circle');
if (pulseCircle) {
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
}
animationId_input = requestAnimationFrame(updateAudioLevel);
}
updateAudioLevel();
stream.getTracks().forEach(track => {
peerConnection.addTrack(track, stream);
});
// Add connection state change listener
peerConnection.addEventListener('connectionstatechange', () => {
console.log('Connection state:', peerConnection.connectionState);
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
updateButtonState();
});
// Handle incoming audio
peerConnection.addEventListener('track', (evt) => {
if (audioOutput.srcObject !== evt.streams[0]) {
audioOutput.srcObject = evt.streams[0];
audioOutput.play();
// Set up output visualization
analyser_output = audioContext.createAnalyser();
const outputSource = audioContext.createMediaStreamSource(evt.streams[0]);
outputSource.connect(analyser_output);
analyser_output.fftSize = 2048;
dataArray_output = new Uint8Array(analyser_output.frequencyBinCount);
updateVisualization();
}
});
// Create data channel for messages
const dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = (event) => {
const eventJson = JSON.parse(event.data);
const typingIndicator = document.getElementById('typing-indicator');
if (eventJson.type === "error") {
showError(eventJson.message);
} else if (eventJson.type === "send_input") {
fetch('/input_hook', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({
webrtc_id: webrtc_id,
chatbot: chatHistory
})
});
} else if (eventJson.type === "log") {
if (eventJson.data === "pause_detected") {
typingIndicator.style.display = 'block';
chatMessages.scrollTop = chatMessages.scrollHeight;
} else if (eventJson.data === "response_starting") {
typingIndicator.style.display = 'none';
}
}
};
// Create and send offer
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
webrtc_id = Math.random().toString(36).substring(7);
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
return;
}
await peerConnection.setRemoteDescription(serverResponse);
// Start visualization
updateVisualization();
// create event stream to receive messages from /output
const eventSource = new EventSource('/outputs?webrtc_id=' + webrtc_id);
eventSource.addEventListener("output", (event) => {
const eventJson = JSON.parse(event.data);
addMessage(eventJson.role, eventJson.content);
});
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
}
}
function addMessage(role, content) {
const messageDiv = document.createElement('div');
messageDiv.classList.add('message', role);
messageDiv.textContent = content;
chatMessages.appendChild(messageDiv);
chatMessages.scrollTop = chatMessages.scrollHeight;
chatHistory.push({ role, content });
}
// Add this after other const declarations
const boxContainer = document.querySelector('.box-container');
const numBars = 32;
for (let i = 0; i < numBars; i++) {
const box = document.createElement('div');
box.className = 'box';
boxContainer.appendChild(box);
}
// Replace the draw function with updateVisualization
function updateVisualization() {
animationId_output = requestAnimationFrame(updateVisualization);
analyser_output.getByteFrequencyData(dataArray_output);
const bars = document.querySelectorAll('.box');
for (let i = 0; i < bars.length; i++) {
const barHeight = (dataArray_output[i] / 255) * 2;
bars[i].style.transform = `scaleY(${Math.max(0.1, barHeight)})`;
}
}
function stop() {
if (peerConnection) {
if (peerConnection.getTransceivers) {
peerConnection.getTransceivers().forEach(transceiver => {
if (transceiver.stop) {
transceiver.stop();
}
});
}
if (peerConnection.getSenders) {
peerConnection.getSenders().forEach(sender => {
if (sender.track && sender.track.stop) sender.track.stop();
});
}
peerConnection.close();
}
if (animationId_input) {
cancelAnimationFrame(animationId_input);
}
if (animationId_output) {
cancelAnimationFrame(animationId_output);
}
if (audioContext) {
audioContext.close();
}
updateButtonState();
}
startButton.addEventListener('click', () => {
if (startButton.textContent === 'Start') {
setupWebRTC();
} else {
stop();
}
});
</script>
</body>
</html>

6
demo/talk_to_claude/requirements.txt Normal file
View File

@@ -0,0 +1,6 @@
fastrtc[vad, tts]
elevenlabs
groq
anthropic
twilio
python-dotenv

15
demo/talk_to_gemini/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to Gemini
emoji: ♊️
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to Gemini using Google's multimodal API
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GEMINI_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

15
demo/talk_to_gemini/README_gradio.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to Gemini (Gradio UI)
emoji: ♊️
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to Gemini (Gradio UI)
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GEMINI_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

187
demo/talk_to_gemini/app.py Normal file
View File

@@ -0,0 +1,187 @@
import asyncio
import base64
import json
import os
import pathlib
from typing import AsyncGenerator, Literal
import gradio as gr
import numpy as np
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi.responses import HTMLResponse
from fastrtc import (
AsyncStreamHandler,
Stream,
WebRTCError,
get_twilio_turn_credentials,
)
from google import genai
from google.genai.types import (
LiveConnectConfig,
PrebuiltVoiceConfig,
SpeechConfig,
VoiceConfig,
)
from gradio.utils import get_space
from pydantic import BaseModel
current_dir = pathlib.Path(__file__).parent
load_dotenv()
def encode_audio(data: np.ndarray) -> str:
"""Encode Audio data to send to the server"""
return base64.b64encode(data.tobytes()).decode("UTF-8")
class GeminiHandler(AsyncStreamHandler):
"""Handler for the Gemini API"""
def __init__(
self,
expected_layout: Literal["mono"] = "mono",
output_sample_rate: int = 24000,
output_frame_size: int = 480,
) -> None:
super().__init__(
expected_layout,
output_sample_rate,
output_frame_size,
input_sample_rate=16000,
)
self.input_queue: asyncio.Queue = asyncio.Queue()
self.output_queue: asyncio.Queue = asyncio.Queue()
self.quit: asyncio.Event = asyncio.Event()
def copy(self) -> "GeminiHandler":
return GeminiHandler(
expected_layout="mono",
output_sample_rate=self.output_sample_rate,
output_frame_size=self.output_frame_size,
)
async def start_up(self):
if not self.phone_mode:
await self.wait_for_args()
api_key, voice_name = self.latest_args[1:]
else:
api_key, voice_name = None, "Puck"
try:
client = genai.Client(
api_key=api_key or os.getenv("GEMINI_API_KEY"),
http_options={"api_version": "v1alpha"},
)
except Exception as e:
raise WebRTCError(str(e))
config = LiveConnectConfig(
response_modalities=["AUDIO"], # type: ignore
speech_config=SpeechConfig(
voice_config=VoiceConfig(
prebuilt_voice_config=PrebuiltVoiceConfig(
voice_name=voice_name,
)
)
),
)
try:
async with client.aio.live.connect(
model="gemini-2.0-flash-exp", config=config
) as session:
async for audio in session.start_stream(
stream=self.stream(), mime_type="audio/pcm"
):
if audio.data:
array = np.frombuffer(audio.data, dtype=np.int16)
self.output_queue.put_nowait(array)
except Exception as e:
raise WebRTCError(str(e))
async def stream(self) -> AsyncGenerator[bytes, None]:
while not self.quit.is_set():
try:
audio = await asyncio.wait_for(self.input_queue.get(), 0.1)
yield audio
except (asyncio.TimeoutError, TimeoutError):
pass
async def receive(self, frame: tuple[int, np.ndarray]) -> None:
_, array = frame
array = array.squeeze()
audio_message = encode_audio(array)
self.input_queue.put_nowait(audio_message)
async def emit(self) -> tuple[int, np.ndarray]:
array = await self.output_queue.get()
return (self.output_sample_rate, array)
def shutdown(self) -> None:
self.quit.set()
self.args_set.clear()
stream = Stream(
modality="audio",
mode="send-receive",
handler=GeminiHandler(),
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
additional_inputs=[
gr.Textbox(
label="API Key",
type="password",
value=os.getenv("GEMINI_API_KEY") if not get_space() else "",
),
gr.Dropdown(
label="Voice",
choices=[
"Puck",
"Charon",
"Kore",
"Fenrir",
"Aoede",
],
value="Puck",
),
],
)
class InputData(BaseModel):
webrtc_id: str
voice_name: str
api_key: str
app = FastAPI()
stream.mount(app)
@app.post("/input_hook")
async def _(body: InputData):
stream.set_input(body.webrtc_id, body.api_key, body.voice_name)
return {"status": "ok"}
@app.get("/")
async def index():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (current_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content)
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

452
demo/talk_to_gemini/index.html Normal file
View File

@@ -0,0 +1,452 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Gemini Voice Chat</title>
<style>
:root {
--color-accent: #6366f1;
--color-background: #0f172a;
--color-surface: #1e293b;
--color-text: #e2e8f0;
--boxSize: 8px;
--gutter: 4px;
}
body {
margin: 0;
padding: 0;
background-color: var(--color-background);
color: var(--color-text);
font-family: system-ui, -apple-system, sans-serif;
min-height: 100vh;
display: flex;
flex-direction: column;
align-items: center;
justify-content: center;
}
.container {
width: 90%;
max-width: 800px;
background-color: var(--color-surface);
padding: 2rem;
border-radius: 1rem;
box-shadow: 0 25px 50px -12px rgba(0, 0, 0, 0.25);
}
.wave-container {
position: relative;
display: flex;
min-height: 100px;
max-height: 128px;
justify-content: center;
align-items: center;
margin: 2rem 0;
}
.box-container {
display: flex;
justify-content: space-between;
height: 64px;
width: 100%;
}
.box {
height: 100%;
width: var(--boxSize);
background: var(--color-accent);
border-radius: 8px;
transition: transform 0.05s ease;
}
.controls {
display: grid;
gap: 1rem;
margin-bottom: 2rem;
}
.input-group {
display: flex;
flex-direction: column;
gap: 0.5rem;
}
label {
font-size: 0.875rem;
font-weight: 500;
}
input,
select {
padding: 0.75rem;
border-radius: 0.5rem;
border: 1px solid rgba(255, 255, 255, 0.1);
background-color: var(--color-background);
color: var(--color-text);
font-size: 1rem;
}
button {
padding: 1rem 2rem;
border-radius: 0.5rem;
border: none;
background-color: var(--color-accent);
color: white;
font-weight: 600;
cursor: pointer;
transition: all 0.2s ease;
}
button:hover {
opacity: 0.9;
transform: translateY(-1px);
}
.icon-with-spinner {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.spinner {
width: 20px;
height: 20px;
border: 2px solid white;
border-top-color: transparent;
border-radius: 50%;
animation: spin 1s linear infinite;
flex-shrink: 0;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
.pulse-container {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.pulse-circle {
width: 20px;
height: 20px;
border-radius: 50%;
background-color: white;
opacity: 0.2;
flex-shrink: 0;
transform: translateX(-0%) scale(var(--audio-level, 1));
transition: transform 0.1s ease;
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div style="text-align: center">
<h1>Gemini Voice Chat</h1>
<p>Speak with Gemini using real-time audio streaming</p>
<p>
Get a Gemini API key
<a href="https://ai.google.dev/gemini-api/docs/api-key">here</a>
</p>
</div>
<div class="container">
<div class="controls">
<div class="input-group">
<label for="api-key">API Key</label>
<input type="password" id="api-key" placeholder="Enter your API key">
</div>
<div class="input-group">
<label for="voice">Voice</label>
<select id="voice">
<option value="Puck">Puck</option>
<option value="Charon">Charon</option>
<option value="Kore">Kore</option>
<option value="Fenrir">Fenrir</option>
<option value="Aoede">Aoede</option>
</select>
</div>
</div>
<div class="wave-container">
<div class="box-container">
<!-- Boxes will be dynamically added here -->
</div>
</div>
<button id="start-button">Start Recording</button>
</div>
<audio id="audio-output"></audio>
<script>
let peerConnection;
let audioContext;
let dataChannel;
let isRecording = false;
let webrtc_id;
const startButton = document.getElementById('start-button');
const apiKeyInput = document.getElementById('api-key');
const voiceSelect = document.getElementById('voice');
const audioOutput = document.getElementById('audio-output');
const boxContainer = document.querySelector('.box-container');
const numBars = 32;
for (let i = 0; i < numBars; i++) {
const box = document.createElement('div');
box.className = 'box';
boxContainer.appendChild(box);
}
function updateButtonState() {
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
startButton.innerHTML = `
<div class="icon-with-spinner">
<div class="spinner"></div>
<span>Connecting...</span>
</div>
`;
} else if (peerConnection && peerConnection.connectionState === 'connected') {
startButton.innerHTML = `
<div class="pulse-container">
<div class="pulse-circle"></div>
<span>Stop Recording</span>
</div>
`;
} else {
startButton.innerHTML = 'Start Recording';
}
}
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.className = 'toast error';
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
async function setupWebRTC() {
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
webrtc_id = Math.random().toString(36).substring(7);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
stream.getTracks().forEach(track => peerConnection.addTrack(track, stream));
// Update audio visualization setup
audioContext = new AudioContext();
analyser_input = audioContext.createAnalyser();
const source = audioContext.createMediaStreamSource(stream);
source.connect(analyser_input);
analyser_input.fftSize = 64;
dataArray_input = new Uint8Array(analyser_input.frequencyBinCount);
function updateAudioLevel() {
analyser_input.getByteFrequencyData(dataArray_input);
const average = Array.from(dataArray_input).reduce((a, b) => a + b, 0) / dataArray_input.length;
const audioLevel = average / 255;
const pulseCircle = document.querySelector('.pulse-circle');
if (pulseCircle) {
console.log("audioLevel", audioLevel);
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
}
animationId = requestAnimationFrame(updateAudioLevel);
}
updateAudioLevel();
// Add connection state change listener
peerConnection.addEventListener('connectionstatechange', () => {
console.log('connectionstatechange', peerConnection.connectionState);
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
updateButtonState();
});
// Handle incoming audio
peerConnection.addEventListener('track', (evt) => {
if (audioOutput && audioOutput.srcObject !== evt.streams[0]) {
audioOutput.srcObject = evt.streams[0];
audioOutput.play();
// Set up audio visualization on the output stream
audioContext = new AudioContext();
analyser = audioContext.createAnalyser();
const source = audioContext.createMediaStreamSource(evt.streams[0]);
source.connect(analyser);
analyser.fftSize = 2048;
dataArray = new Uint8Array(analyser.frequencyBinCount);
updateVisualization();
}
});
// Create data channel for messages
dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = (event) => {
const eventJson = JSON.parse(event.data);
if (eventJson.type === "error") {
showError(eventJson.message);
} else if (eventJson.type === "send_input") {
fetch('/input_hook', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({
webrtc_id: webrtc_id,
api_key: apiKeyInput.value,
voice_name: voiceSelect.value
})
});
}
};
// Create and send offer
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id,
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
startButton.textContent = 'Start Recording';
return;
}
await peerConnection.setRemoteDescription(serverResponse);
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
startButton.textContent = 'Start Recording';
}
}
function updateVisualization() {
if (!analyser) return;
analyser.getByteFrequencyData(dataArray);
const bars = document.querySelectorAll('.box');
for (let i = 0; i < bars.length; i++) {
const barHeight = (dataArray[i] / 255) * 2;
bars[i].style.transform = `scaleY(${Math.max(0.1, barHeight)})`;
}
animationId = requestAnimationFrame(updateVisualization);
}
function stopWebRTC() {
if (peerConnection) {
peerConnection.close();
}
if (animationId) {
cancelAnimationFrame(animationId);
}
if (audioContext) {
audioContext.close();
}
updateButtonState();
}
startButton.addEventListener('click', () => {
if (!isRecording) {
setupWebRTC();
startButton.classList.add('recording');
} else {
stopWebRTC();
startButton.classList.remove('recording');
}
isRecording = !isRecording;
});
</script>
</body>
</html>

4
demo/talk_to_gemini/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc
python-dotenv
google-genai
twilio

15
demo/talk_to_openai/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to OpenAI
emoji: 🗣️
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to OpenAI using their multimodal API
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|OPENAI_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

15
demo/talk_to_openai/README_gradio.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to OpenAI (Gradio UI)
emoji: 🗣️
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Talk to OpenAI (Gradio UI)
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|OPENAI_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

160
demo/talk_to_openai/app.py Normal file
View File

@@ -0,0 +1,160 @@
import asyncio
import base64
import json
from pathlib import Path
import gradio as gr
import numpy as np
import openai
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse
from fastrtc import (
AdditionalOutputs,
AsyncStreamHandler,
Stream,
WebRTCError,
get_twilio_turn_credentials,
)
from gradio.utils import get_space
from openai.types.beta.realtime import ResponseAudioTranscriptDoneEvent
load_dotenv()
cur_dir = Path(__file__).parent
SAMPLE_RATE = 24000
class OpenAIHandler(AsyncStreamHandler):
def __init__(
self,
) -> None:
super().__init__(
expected_layout="mono",
output_sample_rate=SAMPLE_RATE,
output_frame_size=480,
input_sample_rate=SAMPLE_RATE,
)
self.connection = None
self.output_queue = asyncio.Queue()
def copy(self):
return OpenAIHandler()
async def start_up(
self,
):
"""Connect to realtime API. Run forever in separate thread to keep connection open."""
self.client = openai.AsyncOpenAI()
try:
async with self.client.beta.realtime.connect(
model="gpt-4o-mini-realtime-preview-2024-12-17"
) as conn:
await conn.session.update(
session={"turn_detection": {"type": "server_vad"}}
)
self.connection = conn
async for event in self.connection:
if event.type == "response.audio_transcript.done":
await self.output_queue.put(AdditionalOutputs(event))
if event.type == "response.audio.delta":
await self.output_queue.put(
(
self.output_sample_rate,
np.frombuffer(
base64.b64decode(event.delta), dtype=np.int16
).reshape(1, -1),
),
)
except Exception:
import traceback
traceback.print_exc()
raise WebRTCError(str(traceback.format_exc()))
async def receive(self, frame: tuple[int, np.ndarray]) -> None:
if not self.connection:
return
try:
_, array = frame
array = array.squeeze()
audio_message = base64.b64encode(array.tobytes()).decode("utf-8")
await self.connection.input_audio_buffer.append(audio=audio_message) # type: ignore
except Exception as e:
# print traceback
print(f"Error in receive: {str(e)}")
import traceback
traceback.print_exc()
raise WebRTCError(str(traceback.format_exc()))
async def emit(self) -> tuple[int, np.ndarray] | AdditionalOutputs | None:
return await self.output_queue.get()
def reset_state(self):
"""Reset connection state for new recording session"""
self.connection = None
self.args_set.clear()
async def shutdown(self) -> None:
if self.connection:
await self.connection.close()
self.reset_state()
def update_chatbot(chatbot: list[dict], response: ResponseAudioTranscriptDoneEvent):
chatbot.append({"role": "assistant", "content": response.transcript})
return chatbot
chatbot = gr.Chatbot(type="messages")
latest_message = gr.Textbox(type="text", visible=False)
stream = Stream(
OpenAIHandler(),
mode="send-receive",
modality="audio",
additional_inputs=[chatbot],
additional_outputs=[chatbot],
additional_outputs_handler=update_chatbot,
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
)
app = FastAPI()
stream.mount(app)
@app.get("/")
async def _():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (cur_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content)
@app.get("/outputs")
def _(webrtc_id: str):
async def output_stream():
import json
async for output in stream.output_stream(webrtc_id):
s = json.dumps({"role": "assistant", "content": output.args[0].transcript})
yield f"event: output\ndata: {s}\n\n"
return StreamingResponse(output_stream(), media_type="text/event-stream")
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

404
demo/talk_to_openai/index.html Normal file
View File

@@ -0,0 +1,404 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>OpenAI Real-Time Chat</title>
<style>
body {
font-family: "SF Pro Display", -apple-system, BlinkMacSystemFont, sans-serif;
background-color: #0a0a0a;
color: #ffffff;
margin: 0;
padding: 20px;
height: 100vh;
box-sizing: border-box;
}
.container {
max-width: 800px;
margin: 0 auto;
height: calc(100% - 100px);
}
.logo {
text-align: center;
margin-bottom: 40px;
}
.chat-container {
border: 1px solid #333;
padding: 20px;
height: 90%;
box-sizing: border-box;
display: flex;
flex-direction: column;
}
.chat-messages {
flex-grow: 1;
overflow-y: auto;
margin-bottom: 20px;
padding: 10px;
}
.message {
margin-bottom: 20px;
padding: 12px;
border-radius: 4px;
font-size: 16px;
line-height: 1.5;
}
.message.user {
background-color: #1a1a1a;
margin-left: 20%;
}
.message.assistant {
background-color: #262626;
margin-right: 20%;
}
.controls {
text-align: center;
margin-top: 20px;
}
button {
background-color: transparent;
color: #ffffff;
border: 1px solid #ffffff;
padding: 12px 24px;
font-family: inherit;
font-size: 16px;
cursor: pointer;
transition: all 0.3s;
text-transform: uppercase;
letter-spacing: 1px;
}
button:hover {
border-width: 2px;
transform: scale(1.02);
box-shadow: 0 0 10px rgba(255, 255, 255, 0.2);
}
#audio-output {
display: none;
}
.icon-with-spinner {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.spinner {
width: 20px;
height: 20px;
border: 2px solid #ffffff;
border-top-color: transparent;
border-radius: 50%;
animation: spin 1s linear infinite;
flex-shrink: 0;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
.pulse-container {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.pulse-circle {
width: 20px;
height: 20px;
border-radius: 50%;
background-color: #ffffff;
opacity: 0.2;
flex-shrink: 0;
transform: translateX(-0%) scale(var(--audio-level, 1));
transition: transform 0.1s ease;
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div class="container">
<div class="logo">
<h1>OpenAI Real-Time Chat</h1>
</div>
<div class="chat-container">
<div class="chat-messages" id="chat-messages"></div>
</div>
<div class="controls">
<button id="start-button">Start Conversation</button>
</div>
</div>
<audio id="audio-output"></audio>
<script>
let peerConnection;
let webrtc_id;
const audioOutput = document.getElementById('audio-output');
const startButton = document.getElementById('start-button');
const chatMessages = document.getElementById('chat-messages');
let audioLevel = 0;
let animationFrame;
let audioContext, analyser, audioSource;
function updateButtonState() {
const button = document.getElementById('start-button');
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
button.innerHTML = `
<div class="icon-with-spinner">
<div class="spinner"></div>
<span>Connecting...</span>
</div>
`;
} else if (peerConnection && peerConnection.connectionState === 'connected') {
button.innerHTML = `
<div class="pulse-container">
<div class="pulse-circle"></div>
<span>Stop Conversation</span>
</div>
`;
} else {
button.innerHTML = 'Start Conversation';
}
}
function setupAudioVisualization(stream) {
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
audioSource = audioContext.createMediaStreamSource(stream);
audioSource.connect(analyser);
analyser.fftSize = 64;
const dataArray = new Uint8Array(analyser.frequencyBinCount);
function updateAudioLevel() {
analyser.getByteFrequencyData(dataArray);
const average = Array.from(dataArray).reduce((a, b) => a + b, 0) / dataArray.length;
audioLevel = average / 255;
// Update CSS variable instead of rebuilding the button
const pulseCircle = document.querySelector('.pulse-circle');
if (pulseCircle) {
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
}
animationFrame = requestAnimationFrame(updateAudioLevel);
}
updateAudioLevel();
}
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
async function setupWebRTC() {
isConnecting = true;
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({
audio: true
});
setupAudioVisualization(stream);
stream.getTracks().forEach(track => {
peerConnection.addTrack(track, stream);
});
peerConnection.addEventListener('track', (evt) => {
if (audioOutput.srcObject !== evt.streams[0]) {
audioOutput.srcObject = evt.streams[0];
audioOutput.play();
}
});
const dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = (event) => {
const eventJson = JSON.parse(event.data);
if (eventJson.type === "error") {
showError(eventJson.message);
}
};
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
peerConnection.addEventListener('connectionstatechange', () => {
console.log('connectionstatechange', peerConnection.connectionState);
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
updateButtonState();
});
webrtc_id = Math.random().toString(36).substring(7);
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
return;
}
await peerConnection.setRemoteDescription(serverResponse);
const eventSource = new EventSource('/outputs?webrtc_id=' + webrtc_id);
eventSource.addEventListener("output", (event) => {
const eventJson = JSON.parse(event.data);
addMessage("assistant", eventJson.content);
});
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
}
}
function addMessage(role, content) {
const messageDiv = document.createElement('div');
messageDiv.classList.add('message', role);
messageDiv.textContent = content;
chatMessages.appendChild(messageDiv);
chatMessages.scrollTop = chatMessages.scrollHeight;
}
function stop() {
if (animationFrame) {
cancelAnimationFrame(animationFrame);
}
if (audioContext) {
audioContext.close();
audioContext = null;
analyser = null;
audioSource = null;
}
if (peerConnection) {
if (peerConnection.getTransceivers) {
peerConnection.getTransceivers().forEach(transceiver => {
if (transceiver.stop) {
transceiver.stop();
}
});
}
if (peerConnection.getSenders) {
peerConnection.getSenders().forEach(sender => {
if (sender.track && sender.track.stop) sender.track.stop();
});
}
console.log('closing');
peerConnection.close();
}
updateButtonState();
audioLevel = 0;
}
startButton.addEventListener('click', () => {
console.log('clicked');
console.log(peerConnection, peerConnection?.connectionState);
if (!peerConnection || peerConnection.connectionState !== 'connected') {
setupWebRTC();
} else {
console.log('stopping');
stop();
}
});
</script>
</body>
</html>

4
demo/talk_to_openai/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc[vad]
openai
twilio
python-dotenv

15
demo/talk_to_sambanova/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to Sambanova
emoji: 💻
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Llama 3.2 - SambaNova API
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|SAMBANOVA_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

15
demo/talk_to_sambanova/README_gradio.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Talk to Sambanova (Gradio)
emoji: 💻
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Llama 3.2 - SambaNova API (Gradio)
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|SAMBANOVA_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

152
demo/talk_to_sambanova/app.py Normal file
View File

@@ -0,0 +1,152 @@
import base64
import json
import os
from pathlib import Path
import gradio as gr
import numpy as np
import openai
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse
from fastrtc import (
AdditionalOutputs,
ReplyOnPause,
Stream,
WebRTCError,
get_stt_model,
get_twilio_turn_credentials,
)
from gradio.utils import get_space
from pydantic import BaseModel
load_dotenv()
curr_dir = Path(__file__).parent
client = openai.OpenAI(
api_key=os.environ.get("SAMBANOVA_API_KEY"),
base_url="https://api.sambanova.ai/v1",
)
stt_model = get_stt_model()
def response(
audio: tuple[int, np.ndarray],
gradio_chatbot: list[dict] | None = None,
conversation_state: list[dict] | None = None,
):
gradio_chatbot = gradio_chatbot or []
conversation_state = conversation_state or []
text = stt_model.stt(audio)
sample_rate, array = audio
gradio_chatbot.append(
{"role": "user", "content": gr.Audio((sample_rate, array.squeeze()))}
)
yield AdditionalOutputs(gradio_chatbot, conversation_state)
conversation_state.append({"role": "user", "content": text})
try:
request = client.chat.completions.create(
model="Meta-Llama-3.2-3B-Instruct",
messages=conversation_state, # type: ignore
temperature=0.1,
top_p=0.1,
)
response = {"role": "assistant", "content": request.choices[0].message.content}
except Exception:
import traceback
traceback.print_exc()
raise WebRTCError(traceback.format_exc())
conversation_state.append(response)
gradio_chatbot.append(response)
yield AdditionalOutputs(gradio_chatbot, conversation_state)
chatbot = gr.Chatbot(type="messages", value=[])
state = gr.State(value=[])
stream = Stream(
ReplyOnPause(
response, # type: ignore
input_sample_rate=16000,
),
mode="send",
modality="audio",
additional_inputs=[chatbot, state],
additional_outputs=[chatbot, state],
additional_outputs_handler=lambda *a: (a[2], a[3]),
concurrency_limit=20 if get_space() else None,
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
)
app = FastAPI()
stream.mount(app)
class Message(BaseModel):
role: str
content: str
class InputData(BaseModel):
webrtc_id: str
chatbot: list[Message]
state: list[Message]
@app.get("/")
async def _():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (curr_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content)
@app.post("/input_hook")
async def _(data: InputData):
body = data.model_dump()
stream.set_input(data.webrtc_id, body["chatbot"], body["state"])
def audio_to_base64(file_path):
audio_format = "wav"
with open(file_path, "rb") as audio_file:
encoded_audio = base64.b64encode(audio_file.read()).decode("utf-8")
return f"data:audio/{audio_format};base64,{encoded_audio}"
@app.get("/outputs")
async def _(webrtc_id: str):
async def output_stream():
async for output in stream.output_stream(webrtc_id):
chatbot = output.args[0]
state = output.args[1]
data = {
"message": state[-1],
"audio": audio_to_base64(chatbot[-1]["content"].value["path"])
if chatbot[-1]["role"] == "user"
else None,
}
yield f"event: output\ndata: {json.dumps(data)}\n\n"
return StreamingResponse(output_stream(), media_type="text/event-stream")
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860)
elif mode == "PHONE":
raise ValueError("Phone mode not supported")
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

487
demo/talk_to_sambanova/index.html Normal file
View File

@@ -0,0 +1,487 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Talk to Sambanova</title>
<style>
body {
font-family: -apple-system, BlinkMacSystemFont, "Segoe UI", Roboto, sans-serif;
background-color: #f8f9fa;
color: #1a1a1a;
margin: 0;
padding: 20px;
height: 100vh;
box-sizing: border-box;
}
.container {
max-width: 800px;
margin: 0 auto;
height: 80%;
}
.logo {
text-align: center;
margin-bottom: 40px;
}
.chat-container {
background: white;
border-radius: 8px;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
padding: 20px;
height: 90%;
box-sizing: border-box;
display: flex;
flex-direction: column;
}
.chat-messages {
flex-grow: 1;
overflow-y: auto;
margin-bottom: 20px;
padding: 10px;
}
.message {
margin-bottom: 20px;
padding: 12px;
border-radius: 8px;
font-size: 14px;
line-height: 1.5;
}
.message.user {
background-color: #e9ecef;
margin-left: 20%;
}
.message.assistant {
background-color: #f1f3f5;
margin-right: 20%;
}
.controls {
text-align: center;
margin-top: 20px;
}
button {
background-color: #0066cc;
color: white;
border: none;
padding: 12px 24px;
font-family: inherit;
font-size: 14px;
cursor: pointer;
transition: all 0.3s;
border-radius: 4px;
font-weight: 500;
}
button:hover {
background-color: #0052a3;
}
#audio-output {
display: none;
}
.icon-with-spinner {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.spinner {
width: 20px;
height: 20px;
border: 2px solid #ffffff;
border-top-color: transparent;
border-radius: 50%;
animation: spin 1s linear infinite;
flex-shrink: 0;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
.pulse-container {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.pulse-circle {
width: 20px;
height: 20px;
border-radius: 50%;
background-color: #ffffff;
opacity: 0.2;
flex-shrink: 0;
transform: translateX(-0%) scale(var(--audio-level, 1));
transition: transform 0.1s ease;
}
/* Add styles for typing indicator */
.typing-indicator {
padding: 8px;
background-color: #f1f3f5;
border-radius: 8px;
margin-bottom: 10px;
display: none;
}
.dots {
display: inline-flex;
gap: 4px;
}
.dot {
width: 8px;
height: 8px;
background-color: #0066cc;
border-radius: 50%;
animation: pulse 1.5s infinite;
opacity: 0.5;
}
.dot:nth-child(2) {
animation-delay: 0.5s;
}
.dot:nth-child(3) {
animation-delay: 1s;
}
@keyframes pulse {
0%,
100% {
opacity: 0.5;
transform: scale(1);
}
50% {
opacity: 1;
transform: scale(1.2);
}
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div class="container">
<div class="logo">
<h1>Talk to Sambanova 🗣️</h1>
<h2 style="font-size: 1.2em; color: #666; margin-top: 10px;">Speak to Llama 3.2 powered by Sambanova API
</h2>
</div>
<div class="chat-container">
<div class="chat-messages" id="chat-messages"></div>
<div class="typing-indicator" id="typing-indicator">
<div class="dots">
<div class="dot"></div>
<div class="dot"></div>
<div class="dot"></div>
</div>
</div>
</div>
<div class="controls">
<button id="start-button">Start Conversation</button>
</div>
</div>
<audio id="audio-output"></audio>
<script>
let peerConnection;
let webrtc_id;
const startButton = document.getElementById('start-button');
const chatMessages = document.getElementById('chat-messages');
let audioLevel = 0;
let animationFrame;
let audioContext, analyser, audioSource;
let messages = [];
let eventSource;
function updateButtonState() {
const button = document.getElementById('start-button');
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
button.innerHTML = `
<div class="icon-with-spinner">
<div class="spinner"></div>
<span>Connecting...</span>
</div>
`;
} else if (peerConnection && peerConnection.connectionState === 'connected') {
button.innerHTML = `
<div class="pulse-container">
<div class="pulse-circle"></div>
<span>Stop Conversation</span>
</div>
`;
} else {
button.innerHTML = 'Start Conversation';
}
}
function setupAudioVisualization(stream) {
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
audioSource = audioContext.createMediaStreamSource(stream);
audioSource.connect(analyser);
analyser.fftSize = 64;
const dataArray = new Uint8Array(analyser.frequencyBinCount);
function updateAudioLevel() {
analyser.getByteFrequencyData(dataArray);
const average = Array.from(dataArray).reduce((a, b) => a + b, 0) / dataArray.length;
audioLevel = average / 255;
const pulseCircle = document.querySelector('.pulse-circle');
if (pulseCircle) {
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
}
animationFrame = requestAnimationFrame(updateAudioLevel);
}
updateAudioLevel();
}
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.className = 'toast error';
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
function handleMessage(event) {
const eventJson = JSON.parse(event.data);
const typingIndicator = document.getElementById('typing-indicator');
if (eventJson.type === "error") {
showError(eventJson.message);
} else if (eventJson.type === "send_input") {
fetch('/input_hook', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({
webrtc_id: webrtc_id,
chatbot: messages,
state: messages
})
});
} else if (eventJson.type === "log") {
if (eventJson.data === "pause_detected") {
typingIndicator.style.display = 'block';
chatMessages.scrollTop = chatMessages.scrollHeight;
} else if (eventJson.data === "response_starting") {
typingIndicator.style.display = 'none';
}
}
}
async function setupWebRTC() {
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({
audio: true
});
setupAudioVisualization(stream);
stream.getTracks().forEach(track => {
peerConnection.addTrack(track, stream);
});
const dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = handleMessage;
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
peerConnection.addEventListener('connectionstatechange', () => {
console.log('connectionstatechange', peerConnection.connectionState);
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
updateButtonState();
});
webrtc_id = Math.random().toString(36).substring(7);
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
return;
}
await peerConnection.setRemoteDescription(serverResponse);
eventSource = new EventSource('/outputs?webrtc_id=' + webrtc_id);
eventSource.addEventListener("output", (event) => {
const eventJson = JSON.parse(event.data);
console.log(eventJson);
messages.push(eventJson.message);
addMessage(eventJson.message.role, eventJson.audio ?? eventJson.message.content);
});
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
}
}
function addMessage(role, content) {
const messageDiv = document.createElement('div');
messageDiv.classList.add('message', role);
if (role === 'user') {
// Create audio element for user messages
const audio = document.createElement('audio');
audio.controls = true;
audio.src = content;
messageDiv.appendChild(audio);
} else {
// Text content for assistant messages
messageDiv.textContent = content;
}
chatMessages.appendChild(messageDiv);
chatMessages.scrollTop = chatMessages.scrollHeight;
}
function stop() {
if (eventSource) {
eventSource.close();
eventSource = null;
}
if (animationFrame) {
cancelAnimationFrame(animationFrame);
}
if (audioContext) {
audioContext.close();
audioContext = null;
analyser = null;
audioSource = null;
}
if (peerConnection) {
if (peerConnection.getTransceivers) {
peerConnection.getTransceivers().forEach(transceiver => {
if (transceiver.stop) {
transceiver.stop();
}
});
}
if (peerConnection.getSenders) {
peerConnection.getSenders().forEach(sender => {
if (sender.track && sender.track.stop) sender.track.stop();
});
}
peerConnection.close();
}
updateButtonState();
audioLevel = 0;
}
startButton.addEventListener('click', () => {
if (!peerConnection || peerConnection.connectionState !== 'connected') {
setupWebRTC();
} else {
stop();
}
});
</script>
</body>
</html>

4
demo/talk_to_sambanova/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc[vad, stt]
python-dotenv
openai
twilio

65
demo/video_out.py
View File

@@ -1,65 +0,0 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation(input_video):
cap = cv2.VideoCapture(input_video)
iterating = True
while iterating:
iterating, frame = cap.read()
# flip frame vertically
frame = cv2.flip(frame, 0)
display_frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
yield display_frame
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Video Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
with gr.Row():
with gr.Column():
input_video = gr.Video(sources="upload")
with gr.Column():
output_video = WebRTC(
label="Video Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="video",
)
output_video.stream(
fn=generation,
inputs=[input_video],
outputs=[output_video],
trigger=input_video.upload,
)
if __name__ == "__main__":
demo.launch()

54
demo/video_out_stream.py
View File

@@ -1,54 +0,0 @@
import os
import cv2
import gradio as gr
from gradio_webrtc import WebRTC
from twilio.rest import Client
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def generation():
url = "https://download.tsi.telecom-paristech.fr/gpac/dataset/dash/uhd/mux_sources/hevcds_720p30_2M.mp4"
cap = cv2.VideoCapture(url)
iterating = True
while iterating:
iterating, frame = cap.read()
yield frame
with gr.Blocks() as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
Video Streaming (Powered by WebRTC ⚡️)
</h1>
"""
)
output_video = WebRTC(
label="Video Stream",
rtc_configuration=rtc_configuration,
mode="receive",
modality="video",
)
button = gr.Button("Start", variant="primary")
output_video.stream(
fn=generation, inputs=None, outputs=[output_video], trigger=button.click
)
if __name__ == "__main__":
demo.launch()

102
demo/video_send_output.py
View File

@@ -1,102 +0,0 @@
import logging
import os
import random
import cv2
import gradio as gr
from gradio_webrtc import AdditionalOutputs, WebRTC
from huggingface_hub import hf_hub_download
from inference import YOLOv10
from twilio.rest import Client
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.FileHandler("gradio_webrtc.log")
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("gradio_webrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
model_file = hf_hub_download(
repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)
model = YOLOv10(model_file)
account_sid = os.environ.get("TWILIO_ACCOUNT_SID")
auth_token = os.environ.get("TWILIO_AUTH_TOKEN")
if account_sid and auth_token:
client = Client(account_sid, auth_token)
token = client.tokens.create()
rtc_configuration = {
"iceServers": token.ice_servers,
"iceTransportPolicy": "relay",
}
else:
rtc_configuration = None
def detection(image, conf_threshold=0.3):
image = cv2.resize(image, (model.input_width, model.input_height))
new_image = model.detect_objects(image, conf_threshold)
return cv2.resize(new_image, (500, 500))
css = """.my-group {max-width: 600px !important; max-height: 600 !important;}
.my-column {display: flex !important; justify-content: center !important; align-items: center !important};"""
with gr.Blocks(css=css) as demo:
gr.HTML(
"""
<h1 style='text-align: center'>
YOLOv10 Webcam Stream (Powered by WebRTC ⚡️)
</h1>
"""
)
gr.HTML(
"""
<h3 style='text-align: center'>
<a href='https://arxiv.org/abs/2405.14458' target='_blank'>arXiv</a> | <a href='https://github.com/THU-MIG/yolov10' target='_blank'>github</a>
</h3>
"""
)
with gr.Column(elem_classes=["my-column"]):
with gr.Group(elem_classes=["my-group"]):
image = WebRTC(
label="Stream",
rtc_configuration=rtc_configuration,
mode="send-receive",
modality="video",
track_constraints={
"width": {"exact": 800},
"height": {"exact": 600},
"aspectRatio": {"exact": 1.33333},
},
rtp_params={"degradationPreference": "maintain-resolution"},
)
conf_threshold = gr.Slider(
label="Confidence Threshold",
minimum=0.0,
maximum=1.0,
step=0.05,
value=0.30,
)
number = gr.Number()
image.stream(
fn=detection, inputs=[image, conf_threshold], outputs=[image], time_limit=90
)
demo.launch()

15
demo/webrtc_vs_websocket/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Webrtc Vs Websocket
emoji: 🧪
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Compare Round Trip Times between WebRTC and Websockets
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|ELEVENLABS_API_KEY, secret|GROQ_API_KEY, secret|ANTHROPIC_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

147
demo/webrtc_vs_websocket/app.py Normal file
View File

@@ -0,0 +1,147 @@
import json
import logging
import os
from pathlib import Path
import anthropic
import gradio as gr
import numpy as np
from dotenv import load_dotenv
from elevenlabs import ElevenLabs
from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse
from fastrtc import AdditionalOutputs, ReplyOnPause, Stream, get_twilio_turn_credentials
from fastrtc.utils import aggregate_bytes_to_16bit, audio_to_bytes
from gradio.utils import get_space
from groq import Groq
from pydantic import BaseModel
# Configure the root logger to WARNING to suppress debug messages from other libraries
logging.basicConfig(level=logging.WARNING)
# Create a console handler
console_handler = logging.FileHandler("gradio_webrtc.log")
console_handler.setLevel(logging.DEBUG)
# Create a formatter
formatter = logging.Formatter("%(asctime)s - %(name)s - %(levelname)s - %(message)s")
console_handler.setFormatter(formatter)
# Configure the logger for your specific library
logger = logging.getLogger("fastrtc")
logger.setLevel(logging.DEBUG)
logger.addHandler(console_handler)
load_dotenv()
groq_client = Groq()
claude_client = anthropic.Anthropic()
tts_client = ElevenLabs(api_key=os.environ["ELEVENLABS_API_KEY"])
curr_dir = Path(__file__).parent
def response(
audio: tuple[int, np.ndarray],
chatbot: list[dict] | None = None,
):
chatbot = chatbot or []
messages = [{"role": d["role"], "content": d["content"]} for d in chatbot]
prompt = groq_client.audio.transcriptions.create(
file=("audio-file.mp3", audio_to_bytes(audio)),
model="whisper-large-v3-turbo",
response_format="verbose_json",
).text
print("prompt", prompt)
chatbot.append({"role": "user", "content": prompt})
messages.append({"role": "user", "content": prompt})
response = claude_client.messages.create(
model="claude-3-5-haiku-20241022",
max_tokens=512,
messages=messages, # type: ignore
)
response_text = " ".join(
block.text # type: ignore
for block in response.content
if getattr(block, "type", None) == "text"
)
chatbot.append({"role": "assistant", "content": response_text})
yield AdditionalOutputs(chatbot)
iterator = tts_client.text_to_speech.convert_as_stream(
text=response_text,
voice_id="JBFqnCBsd6RMkjVDRZzb",
model_id="eleven_multilingual_v2",
output_format="pcm_24000",
)
for chunk in aggregate_bytes_to_16bit(iterator):
audio_array = np.frombuffer(chunk, dtype=np.int16).reshape(1, -1)
yield (24000, audio_array, "mono")
chatbot = gr.Chatbot(type="messages")
stream = Stream(
modality="audio",
mode="send-receive",
handler=ReplyOnPause(response),
additional_outputs_handler=lambda a, b: b,
additional_inputs=[chatbot],
additional_outputs=[chatbot],
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=20 if get_space() else None,
)
class Message(BaseModel):
role: str
content: str
class InputData(BaseModel):
webrtc_id: str
chatbot: list[Message]
app = FastAPI()
stream.mount(app)
@app.get("/")
async def _():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (curr_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content, status_code=200)
@app.post("/input_hook")
async def _(body: InputData):
stream.set_input(body.webrtc_id, body.model_dump()["chatbot"])
return {"status": "ok"}
@app.get("/outputs")
def _(webrtc_id: str):
print("outputs", webrtc_id)
async def output_stream():
async for output in stream.output_stream(webrtc_id):
chatbot = output.args[0]
yield f"event: output\ndata: {json.dumps(chatbot[-2])}\n\n"
yield f"event: output\ndata: {json.dumps(chatbot[-1])}\n\n"
return StreamingResponse(output_stream(), media_type="text/event-stream")
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860, server_name="0.0.0.0")
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

630
demo/webrtc_vs_websocket/index.html Normal file
View File

@@ -0,0 +1,630 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>WebRTC vs WebSocket Benchmark</title>
<script src="https://cdn.jsdelivr.net/npm/alawmulaw"></script>
<style>
body {
font-family: system-ui, -apple-system, sans-serif;
margin: 0;
padding: 20px;
background-color: #f5f5f5;
}
.container {
display: grid;
grid-template-columns: 1fr 1fr;
gap: 30px;
max-width: 1400px;
margin: 0 auto;
}
.panel {
background: white;
border-radius: 12px;
padding: 20px;
box-shadow: 0 2px 4px rgba(0, 0, 0, 0.1);
}
.chat-container {
height: 400px;
overflow-y: auto;
border: 1px solid #e0e0e0;
border-radius: 8px;
padding: 15px;
margin-bottom: 15px;
}
.message {
margin-bottom: 10px;
padding: 8px 12px;
border-radius: 8px;
max-width: 80%;
}
.message.user {
background-color: #e3f2fd;
margin-left: auto;
}
.message.assistant {
background-color: #f5f5f5;
}
.metrics {
margin-top: 15px;
padding: 10px;
background: #f8f9fa;
border-radius: 8px;
}
.metric {
margin: 5px 0;
font-size: 14px;
}
button {
background-color: #1976d2;
color: white;
border: none;
padding: 10px 20px;
border-radius: 6px;
cursor: pointer;
font-size: 14px;
transition: background-color 0.2s;
}
button:hover {
background-color: #1565c0;
}
button:disabled {
background-color: #bdbdbd;
cursor: not-allowed;
}
h2 {
margin-top: 0;
color: #1976d2;
}
.visualizer {
width: 100%;
height: 100px;
margin: 10px 0;
background: #fafafa;
border-radius: 8px;
}
/* Add styles for disclaimer */
.disclaimer {
background-color: #fff3e0;
padding: 15px;
border-radius: 8px;
margin-bottom: 20px;
font-size: 14px;
line-height: 1.5;
max-width: 1400px;
margin: 0 auto 20px auto;
}
/* Update nav bar styles */
.nav-bar {
background-color: #f5f5f5;
padding: 10px 20px;
margin-bottom: 20px;
}
.nav-container {
max-width: 1400px;
margin: 0 auto;
display: flex;
gap: 10px;
}
.nav-button {
background-color: #1976d2;
color: white;
border: none;
padding: 8px 16px;
border-radius: 4px;
cursor: pointer;
text-decoration: none;
font-size: 14px;
transition: background-color 0.2s;
}
.nav-button:hover {
background-color: #1565c0;
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
</style>
</head>
<body>
<nav class="nav-bar">
<div class="nav-container">
<a href="./webrtc/docs" class="nav-button">WebRTC Docs</a>
<a href="./websocket/docs" class="nav-button">WebSocket Docs</a>
<a href="./telephone/docs" class="nav-button">Telephone Docs</a>
<a href="./ui" class="nav-button">UI</a>
</div>
</nav>
<div class="disclaimer">
This page compares the WebRTC Round-Trip-Time calculated from <code>getStats()</code> to the time taken to
process a ping/pong response pattern over websockets. It may not be a gold standard benchmark. Both WebRTC and
Websockets have their merits/advantages which is why FastRTC supports both. Artifacts in the WebSocket playback
audio are due to gaps in my frontend processing code and not FastRTC web server.
</div>
<div class="container">
<div class="panel">
<h2>WebRTC Connection</h2>
<div id="webrtc-chat" class="chat-container"></div>
<div id="webrtc-metrics" class="metrics">
<div class="metric">RTT (Round Trip Time): <span id="webrtc-rtt">-</span></div>
</div>
<button id="webrtc-button">Connect WebRTC</button>
</div>
<div class="panel">
<h2>WebSocket Connection</h2>
<div id="ws-chat" class="chat-container"></div>
<div id="ws-metrics" class="metrics">
<div class="metric">RTT (Round Trip Time): <span id="ws-rtt">0</span></div>
</div>
<button id="ws-button">Connect WebSocket</button>
</div>
</div>
<audio id="webrtc-audio" style="display: none;"></audio>
<audio id="ws-audio" style="display: none;"></audio>
<div id="error-toast" class="toast"></div>
<script>
// Shared utilities
function generateId() {
return Math.random().toString(36).substring(7);
}
function sendInput(id) {
return function handleMessage(event) {
const eventJson = JSON.parse(event.data);
if (eventJson.type === "send_input") {
fetch('/input_hook', {
method: 'POST',
headers: {
'Content-Type': 'application/json',
},
body: JSON.stringify({
webrtc_id: id,
chatbot: chatHistoryWebRTC
})
});
}
}
}
let chatHistoryWebRTC = [];
let chatHistoryWebSocket = [];
function addMessage(containerId, role, content) {
const container = document.getElementById(containerId);
const messageDiv = document.createElement('div');
messageDiv.classList.add('message', role);
messageDiv.textContent = content;
container.appendChild(messageDiv);
container.scrollTop = container.scrollHeight;
if (containerId === 'webrtc-chat') {
chatHistoryWebRTC.push({ role, content });
} else {
chatHistoryWebSocket.push({ role, content });
}
}
// WebRTC Implementation
let webrtcPeerConnection;
// Add this function to collect RTT stats
async function updateWebRTCStats() {
if (!webrtcPeerConnection) return;
const stats = await webrtcPeerConnection.getStats();
stats.forEach(report => {
if (report.type === 'candidate-pair' && report.state === 'succeeded') {
const rtt = report.currentRoundTripTime * 1000; // Convert to ms
document.getElementById('webrtc-rtt').textContent = `${rtt.toFixed(2)}ms`;
}
});
}
async function setupWebRTC() {
const button = document.getElementById('webrtc-button');
button.textContent = "Stop";
const config = __RTC_CONFIGURATION__;
webrtcPeerConnection = new RTCPeerConnection(config);
const webrtcId = generateId();
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({ audio: true });
stream.getTracks().forEach(track => {
webrtcPeerConnection.addTrack(track, stream);
});
webrtcPeerConnection.addEventListener('track', (evt) => {
const audio = document.getElementById('webrtc-audio');
if (audio.srcObject !== evt.streams[0]) {
audio.srcObject = evt.streams[0];
audio.play();
}
});
const dataChannel = webrtcPeerConnection.createDataChannel('text');
dataChannel.onmessage = sendInput(webrtcId);
const offer = await webrtcPeerConnection.createOffer();
await webrtcPeerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (webrtcPeerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (webrtcPeerConnection.iceGatheringState === "complete") {
webrtcPeerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
webrtcPeerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: webrtcPeerConnection.localDescription.sdp,
type: webrtcPeerConnection.localDescription.type,
webrtc_id: webrtcId
})
});
const serverResponse = await response.json();
await webrtcPeerConnection.setRemoteDescription(serverResponse);
// Setup event source for messages
const eventSource = new EventSource('/outputs?webrtc_id=' + webrtcId);
eventSource.addEventListener("output", (event) => {
const eventJson = JSON.parse(event.data);
addMessage('webrtc-chat', eventJson.role, eventJson.content);
});
// Add periodic stats collection
const statsInterval = setInterval(updateWebRTCStats, 1000);
// Store the interval ID on the connection
webrtcPeerConnection.statsInterval = statsInterval;
webrtcPeerConnection.addEventListener('connectionstatechange', () => {
if (webrtcPeerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
});
} catch (err) {
clearTimeout(timeoutId);
console.error('WebRTC setup error:', err);
}
}
function webrtc_stop() {
if (webrtcPeerConnection) {
// Clear the stats interval
if (webrtcPeerConnection.statsInterval) {
clearInterval(webrtcPeerConnection.statsInterval);
}
// Close all tracks
webrtcPeerConnection.getSenders().forEach(sender => {
if (sender.track) {
sender.track.stop();
}
});
webrtcPeerConnection.close();
webrtcPeerConnection = null;
// Reset metrics display
document.getElementById('webrtc-rtt').textContent = '-';
}
}
// WebSocket Implementation
let webSocket;
let wsMetrics = {
pingStartTime: 0,
rttValues: []
};
// Load mu-law library
// Add load promise to track when the script is ready
function resample(audioData, fromSampleRate, toSampleRate) {
const ratio = fromSampleRate / toSampleRate;
const newLength = Math.round(audioData.length / ratio);
const result = new Float32Array(newLength);
for (let i = 0; i < newLength; i++) {
const position = i * ratio;
const index = Math.floor(position);
const fraction = position - index;
if (index + 1 < audioData.length) {
result[i] = audioData[index] * (1 - fraction) + audioData[index + 1] * fraction;
} else {
result[i] = audioData[index];
}
}
return result;
}
function convertToMulaw(audioData, sampleRate) {
// Resample to 8000 Hz if needed
if (sampleRate !== 8000) {
audioData = resample(audioData, sampleRate, 8000);
}
// Convert float32 [-1,1] to int16 [-32768,32767]
const int16Data = new Int16Array(audioData.length);
for (let i = 0; i < audioData.length; i++) {
int16Data[i] = Math.floor(audioData[i] * 32768);
}
// Convert to mu-law using the library
return alawmulaw.mulaw.encode(int16Data);
}
async function setupWebSocket() {
const button = document.getElementById('ws-button');
button.textContent = "Stop";
try {
const stream = await navigator.mediaDevices.getUserMedia({
audio: {
"echoCancellation": true,
"noiseSuppression": { "exact": true },
"autoGainControl": { "exact": true },
"sampleRate": { "ideal": 24000 },
"sampleSize": { "ideal": 16 },
"channelCount": { "exact": 1 },
}
});
const wsId = generateId();
wsMetrics.startTime = performance.now();
// Create audio context and analyser for visualization
const audioContext = new AudioContext();
const analyser = audioContext.createAnalyser();
const source = audioContext.createMediaStreamSource(stream);
source.connect(analyser);
// Connect to websocket endpoint
webSocket = new WebSocket(`${window.location.protocol === 'https:' ? 'wss:' : 'ws:'}//${window.location.host}/websocket/offer`);
webSocket.onopen = () => {
// Send initial start message
webSocket.send(JSON.stringify({
event: "start",
websocket_id: wsId
}));
// Setup audio processing
const processor = audioContext.createScriptProcessor(2048, 1, 1);
source.connect(processor);
processor.connect(audioContext.destination);
processor.onaudioprocess = (e) => {
const inputData = e.inputBuffer.getChannelData(0);
const mulawData = convertToMulaw(inputData, audioContext.sampleRate);
const base64Audio = btoa(String.fromCharCode.apply(null, mulawData));
if (webSocket.readyState === WebSocket.OPEN) {
webSocket.send(JSON.stringify({
event: "media",
media: {
payload: base64Audio
}
}));
}
};
// Add ping interval
webSocket.pingInterval = setInterval(() => {
wsMetrics.pingStartTime = performance.now();
webSocket.send(JSON.stringify({
event: "ping"
}));
}, 500);
};
// Setup audio output context
const outputContext = new AudioContext({ sampleRate: 24000 });
const sampleRate = 24000; // Updated to match server sample rate
let audioQueue = [];
let isPlaying = false;
webSocket.onmessage = (event) => {
const data = JSON.parse(event.data);
if (data?.type === "send_input") {
console.log("sending input")
fetch('/input_hook', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({ webrtc_id: wsId, chatbot: chatHistoryWebSocket })
});
}
if (data.event === "media") {
// Process received audio
const audioData = atob(data.media.payload);
const mulawData = new Uint8Array(audioData.length);
for (let i = 0; i < audioData.length; i++) {
mulawData[i] = audioData.charCodeAt(i);
}
// Convert mu-law to linear PCM
const linearData = alawmulaw.mulaw.decode(mulawData);
// Create an AudioBuffer
const audioBuffer = outputContext.createBuffer(1, linearData.length, sampleRate);
const channelData = audioBuffer.getChannelData(0);
// Fill the buffer with the decoded data
for (let i = 0; i < linearData.length; i++) {
channelData[i] = linearData[i] / 32768.0;
}
// Queue the audio buffer
audioQueue.push(audioBuffer);
// Start playing if not already playing
if (!isPlaying) {
playNextBuffer();
}
}
// Add pong handler
if (data.event === "pong") {
const rtt = performance.now() - wsMetrics.pingStartTime;
wsMetrics.rttValues.push(rtt);
// Keep only last 20 values for running mean
if (wsMetrics.rttValues.length > 20) {
wsMetrics.rttValues.shift();
}
const avgRtt = wsMetrics.rttValues.reduce((a, b) => a + b, 0) / wsMetrics.rttValues.length;
document.getElementById('ws-rtt').textContent = `${avgRtt.toFixed(2)}ms`;
return;
}
};
function playNextBuffer() {
if (audioQueue.length === 0) {
isPlaying = false;
return;
}
isPlaying = true;
const bufferSource = outputContext.createBufferSource();
bufferSource.buffer = audioQueue.shift();
bufferSource.connect(outputContext.destination);
bufferSource.onended = playNextBuffer;
bufferSource.start();
}
const eventSource = new EventSource('/outputs?webrtc_id=' + wsId);
eventSource.addEventListener("output", (event) => {
console.log("ws output", event);
const eventJson = JSON.parse(event.data);
addMessage('ws-chat', eventJson.role, eventJson.content);
});
} catch (err) {
console.error('WebSocket setup error:', err);
button.disabled = false;
}
}
function ws_stop() {
if (webSocket) {
webSocket.send(JSON.stringify({
event: "stop"
}));
// Clear ping interval
if (webSocket.pingInterval) {
clearInterval(webSocket.pingInterval);
}
// Reset RTT display
document.getElementById('ws-rtt').textContent = '-';
wsMetrics.rttValues = [];
// Clear the stats interval
if (webSocket.statsInterval) {
clearInterval(webSocket.statsInterval);
}
webSocket.close();
}
}
// Event Listeners
document.getElementById('webrtc-button').addEventListener('click', () => {
const button = document.getElementById('webrtc-button');
if (button.textContent === 'Connect WebRTC') {
setupWebRTC();
} else {
webrtc_stop();
button.textContent = 'Connect WebRTC';
}
});
const ws_start_button = document.getElementById('ws-button')
ws_start_button.addEventListener('click', () => {
if (ws_start_button.textContent === 'Connect WebSocket') {
setupWebSocket();
ws_start_button.textContent = 'Stop';
} else {
ws_stop();
ws_start_button.textContent = 'Connect WebSocket';
}
});
document.addEventListener("beforeunload", () => {
ws_stop();
webrtc_stop();
});
</script>
</body>
</html>

6
demo/webrtc_vs_websocket/requirements.txt Normal file
View File

@@ -0,0 +1,6 @@
fastrtc[vad]
elevenlabs
groq
anthropic
twilio
python-dotenv

15
demo/whisper_realtime/README.md Normal file
View File

@@ -0,0 +1,15 @@
---
title: Whisper Realtime Transcription
emoji: 👂
colorFrom: purple
colorTo: red
sdk: gradio
sdk_version: 5.16.0
app_file: app.py
pinned: false
license: mit
short_description: Transcribe audio in realtime with Whisper
tags: [webrtc, websocket, gradio, secret|TWILIO_ACCOUNT_SID, secret|TWILIO_AUTH_TOKEN, secret|GROQ_API_KEY]
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

22
demo/whisper_realtime/README_gradio.md Normal file
View File

@@ -0,0 +1,22 @@
---
app_file: app.py
colorFrom: purple
colorTo: red
emoji: 👂
license: mit
pinned: false
sdk: gradio
sdk_version: 5.16.0
short_description: Transcribe audio in realtime - Gradio UI version
tags:
- webrtc
- websocket
- gradio
- secret|TWILIO_ACCOUNT_SID
- secret|TWILIO_AUTH_TOKEN
- secret|GROQ_API_KEY
title: Whisper Realtime Transcription (Gradio UI)
---
Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

86
demo/whisper_realtime/app.py Normal file
View File

@@ -0,0 +1,86 @@
import json
from pathlib import Path
import gradio as gr
import numpy as np
from dotenv import load_dotenv
from fastapi import FastAPI
from fastapi.responses import HTMLResponse, StreamingResponse
from fastrtc import (
AdditionalOutputs,
ReplyOnPause,
Stream,
WebRTCError,
audio_to_bytes,
get_twilio_turn_credentials,
)
from gradio.utils import get_space
from groq import AsyncClient
cur_dir = Path(__file__).parent
load_dotenv()
groq_client = AsyncClient()
async def transcribe(audio: tuple[int, np.ndarray]):
try:
transcript = await groq_client.audio.transcriptions.create(
file=("audio-file.mp3", audio_to_bytes(audio)),
model="whisper-large-v3-turbo",
response_format="verbose_json",
)
yield AdditionalOutputs(transcript.text)
except Exception as e:
raise WebRTCError(str(e))
stream = Stream(
ReplyOnPause(transcribe),
modality="audio",
mode="send",
additional_outputs=[
gr.Textbox(label="Transcript"),
],
additional_outputs_handler=lambda a, b: a + " " + b,
rtc_configuration=get_twilio_turn_credentials() if get_space() else None,
concurrency_limit=5 if get_space() else None,
time_limit=90 if get_space() else None,
)
app = FastAPI()
stream.mount(app)
@app.get("/transcript")
def _(webrtc_id: str):
async def output_stream():
async for output in stream.output_stream(webrtc_id):
transcript = output.args[0]
yield f"event: output\ndata: {transcript}\n\n"
return StreamingResponse(output_stream(), media_type="text/event-stream")
@app.get("/")
def index():
rtc_config = get_twilio_turn_credentials() if get_space() else None
html_content = (cur_dir / "index.html").read_text()
html_content = html_content.replace("__RTC_CONFIGURATION__", json.dumps(rtc_config))
return HTMLResponse(content=html_content)
if __name__ == "__main__":
import os
if (mode := os.getenv("MODE")) == "UI":
stream.ui.launch(server_port=7860, server_name="0.0.0.0")
elif mode == "PHONE":
stream.fastphone(host="0.0.0.0", port=7860)
else:
import uvicorn
uvicorn.run(app, host="0.0.0.0", port=7860)

424
demo/whisper_realtime/index.html Normal file
View File

@@ -0,0 +1,424 @@
<!DOCTYPE html>
<html lang="en">
<head>
<meta charset="UTF-8">
<meta name="viewport" content="width=device-width, initial-scale=1.0">
<title>Real-time Whisper Transcription</title>
<style>
:root {
--primary-gradient: linear-gradient(135deg, #f9a45c 0%, #e66465 100%);
--background-cream: #faf8f5;
--text-dark: #2d2d2d;
}
body {
font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, Cantarell, sans-serif;
margin: 0;
padding: 0;
background-color: var(--background-cream);
color: var(--text-dark);
min-height: 100vh;
}
.hero {
background: var(--primary-gradient);
color: white;
padding: 2.5rem 2rem;
text-align: center;
}
.hero h1 {
font-size: 2.5rem;
margin: 0;
font-weight: 600;
letter-spacing: -0.5px;
}
.hero p {
font-size: 1rem;
margin-top: 0.5rem;
opacity: 0.9;
}
.container {
max-width: 1000px;
margin: 1.5rem auto;
padding: 0 2rem;
}
.transcript-container {
border-radius: 8px;
box-shadow: 0 2px 8px rgba(0, 0, 0, 0.06);
padding: 1.5rem;
height: 300px;
overflow-y: auto;
margin-bottom: 1.5rem;
border: 1px solid rgba(0, 0, 0, 0.1);
}
.controls {
text-align: center;
margin: 1.5rem 0;
}
button {
background: var(--primary-gradient);
color: white;
border: none;
padding: 10px 20px;
font-size: 0.95rem;
border-radius: 6px;
cursor: pointer;
transition: all 0.2s ease;
font-weight: 500;
min-width: 180px;
}
button:hover {
transform: translateY(-1px);
box-shadow: 0 4px 12px rgba(230, 100, 101, 0.15);
}
button:active {
transform: translateY(0);
}
/* Transcript text styling */
.transcript-container p {
margin: 0.4rem 0;
padding: 0.6rem;
background: var(--background-cream);
border-radius: 4px;
line-height: 1.4;
font-size: 0.95rem;
}
/* Custom scrollbar - made thinner */
.transcript-container::-webkit-scrollbar {
width: 6px;
}
.transcript-container::-webkit-scrollbar-track {
background: var(--background-cream);
border-radius: 3px;
}
.transcript-container::-webkit-scrollbar-thumb {
background: #e66465;
border-radius: 3px;
opacity: 0.8;
}
.transcript-container::-webkit-scrollbar-thumb:hover {
background: #f9a45c;
}
/* Add styles for toast notifications */
.toast {
position: fixed;
top: 20px;
left: 50%;
transform: translateX(-50%);
padding: 16px 24px;
border-radius: 4px;
font-size: 14px;
z-index: 1000;
display: none;
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.2);
}
.toast.error {
background-color: #f44336;
color: white;
}
.toast.warning {
background-color: #ffd700;
color: black;
}
/* Add styles for audio visualization */
.icon-with-spinner {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.spinner {
width: 20px;
height: 20px;
border: 2px solid white;
border-top-color: transparent;
border-radius: 50%;
animation: spin 1s linear infinite;
flex-shrink: 0;
}
.pulse-container {
display: flex;
align-items: center;
justify-content: center;
gap: 12px;
min-width: 180px;
}
.pulse-circle {
width: 20px;
height: 20px;
border-radius: 50%;
background-color: white;
opacity: 0.2;
flex-shrink: 0;
transform: translateX(-0%) scale(var(--audio-level, 1));
transition: transform 0.1s ease;
}
@keyframes spin {
to {
transform: rotate(360deg);
}
}
</style>
</head>
<body>
<!-- Add toast element after body opening tag -->
<div id="error-toast" class="toast"></div>
<div class="hero">
<h1>Real-time Transcription</h1>
<p>Powered by Groq and FastRTC</p>
</div>
<div class="container">
<div class="transcript-container" id="transcript"></div>
<div class="controls">
<button id="start-button">Start Recording</button>
</div>
</div>
<script>
let peerConnection;
let webrtc_id;
let audioContext, analyser, audioSource;
let audioLevel = 0;
let animationFrame;
const startButton = document.getElementById('start-button');
const transcriptDiv = document.getElementById('transcript');
function showError(message) {
const toast = document.getElementById('error-toast');
toast.textContent = message;
toast.style.display = 'block';
// Hide toast after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}
function handleMessage(event) {
// Handle any WebRTC data channel messages if needed
const eventJson = JSON.parse(event.data);
if (eventJson.type === "error") {
showError(eventJson.message);
}
console.log('Received message:', event.data);
}
function updateButtonState() {
if (peerConnection && (peerConnection.connectionState === 'connecting' || peerConnection.connectionState === 'new')) {
startButton.innerHTML = `
<div class="icon-with-spinner">
<div class="spinner"></div>
<span>Connecting...</span>
</div>
`;
} else if (peerConnection && peerConnection.connectionState === 'connected') {
startButton.innerHTML = `
<div class="pulse-container">
<div class="pulse-circle"></div>
<span>Stop Recording</span>
</div>
`;
} else {
startButton.innerHTML = 'Start Recording';
}
}
function setupAudioVisualization(stream) {
audioContext = new (window.AudioContext || window.webkitAudioContext)();
analyser = audioContext.createAnalyser();
audioSource = audioContext.createMediaStreamSource(stream);
audioSource.connect(analyser);
analyser.fftSize = 64;
const dataArray = new Uint8Array(analyser.frequencyBinCount);
function updateAudioLevel() {
analyser.getByteFrequencyData(dataArray);
const average = Array.from(dataArray).reduce((a, b) => a + b, 0) / dataArray.length;
audioLevel = average / 255;
const pulseCircle = document.querySelector('.pulse-circle');
if (pulseCircle) {
pulseCircle.style.setProperty('--audio-level', 1 + audioLevel);
}
animationFrame = requestAnimationFrame(updateAudioLevel);
}
updateAudioLevel();
}
async function setupWebRTC() {
const config = __RTC_CONFIGURATION__;
peerConnection = new RTCPeerConnection(config);
const timeoutId = setTimeout(() => {
const toast = document.getElementById('error-toast');
toast.textContent = "Connection is taking longer than usual. Are you on a VPN?";
toast.className = 'toast warning';
toast.style.display = 'block';
// Hide warning after 5 seconds
setTimeout(() => {
toast.style.display = 'none';
}, 5000);
}, 5000);
try {
const stream = await navigator.mediaDevices.getUserMedia({
audio: true
});
setupAudioVisualization(stream);
stream.getTracks().forEach(track => {
peerConnection.addTrack(track, stream);
});
// Add connection state change listener
peerConnection.addEventListener('connectionstatechange', () => {
console.log('connectionstatechange', peerConnection.connectionState);
if (peerConnection.connectionState === 'connected') {
clearTimeout(timeoutId);
const toast = document.getElementById('error-toast');
toast.style.display = 'none';
}
updateButtonState();
});
// Create data channel for messages
const dataChannel = peerConnection.createDataChannel('text');
dataChannel.onmessage = handleMessage;
// Create and send offer
const offer = await peerConnection.createOffer();
await peerConnection.setLocalDescription(offer);
await new Promise((resolve) => {
if (peerConnection.iceGatheringState === "complete") {
resolve();
} else {
const checkState = () => {
if (peerConnection.iceGatheringState === "complete") {
peerConnection.removeEventListener("icegatheringstatechange", checkState);
resolve();
}
};
peerConnection.addEventListener("icegatheringstatechange", checkState);
}
});
webrtc_id = Math.random().toString(36).substring(7);
const response = await fetch('/webrtc/offer', {
method: 'POST',
headers: { 'Content-Type': 'application/json' },
body: JSON.stringify({
sdp: peerConnection.localDescription.sdp,
type: peerConnection.localDescription.type,
webrtc_id: webrtc_id
})
});
const serverResponse = await response.json();
if (serverResponse.status === 'failed') {
showError(serverResponse.meta.error === 'concurrency_limit_reached'
? `Too many connections. Maximum limit is ${serverResponse.meta.limit}`
: serverResponse.meta.error);
stop();
startButton.textContent = 'Start Recording';
return;
}
await peerConnection.setRemoteDescription(serverResponse);
// Create event stream to receive transcripts
const eventSource = new EventSource('/transcript?webrtc_id=' + webrtc_id);
eventSource.addEventListener("output", (event) => {
appendTranscript(event.data);
});
} catch (err) {
clearTimeout(timeoutId);
console.error('Error setting up WebRTC:', err);
showError('Failed to establish connection. Please try again.');
stop();
startButton.textContent = 'Start Recording';
}
}
function appendTranscript(text) {
const p = document.createElement('p');
p.textContent = text;
transcriptDiv.appendChild(p);
transcriptDiv.scrollTop = transcriptDiv.scrollHeight;
}
function stop() {
if (animationFrame) {
cancelAnimationFrame(animationFrame);
}
if (audioContext) {
audioContext.close();
audioContext = null;
analyser = null;
audioSource = null;
}
if (peerConnection) {
if (peerConnection.getTransceivers) {
peerConnection.getTransceivers().forEach(transceiver => {
if (transceiver.stop) {
transceiver.stop();
}
});
}
if (peerConnection.getSenders) {
peerConnection.getSenders().forEach(sender => {
if (sender.track && sender.track.stop) sender.track.stop();
});
}
setTimeout(() => {
peerConnection.close();
}, 500);
}
audioLevel = 0;
updateButtonState();
}
startButton.addEventListener('click', () => {
if (startButton.textContent === 'Start Recording') {
setupWebRTC();
} else {
stop();
}
});
</script>
</body>
</html>

4
demo/whisper_realtime/requirements.txt Normal file
View File

@@ -0,0 +1,4 @@
fastrtc[vad]
groq
python-dotenv
twilio