gradio-webrtc/README_FASTRTC.md

FastRTC

The Real-Time Communication Library for Python.

Turn any python function into a real-time audio and video stream over WebRTC or WebSockets.

Installation

pip install fastrtc

to use built-in pause detection (see ReplyOnPause), and text to speech (see Text To Speech), install the vad and tts extras:

pip install "fastrtc[vad, tts]"

Key Features

• 🗣️ Automatic Voice Detection and Turn Taking built-in, only worry about the logic for responding to the user.
• 💻 Automatic UI - Use the .ui.launch() method to launch the webRTC-enabled built-in Gradio UI.
• 🔌 Automatic WebRTC Support - Use the .mount(app) method to mount the stream on a FastAPI app and get a webRTC endpoint for your own frontend!
• ⚡️ Websocket Support - Use the .mount(app) method to mount the stream on a FastAPI app and get a websocket endpoint for your own frontend!
• 📞 Automatic Telephone Support - Use the fastphone() method of the stream to launch the application and get a free temporary phone number!
• 🤖 Completely customizable backend - A Stream can easily be mounted on a FastAPI app so you can easily extend it to fit your production application. See the Talk To Claude demo for an example on how to serve a custom JS frontend.

Docs

https://fastrtc.org

Examples

See the Cookbook for examples of how to use the library.

🗣️👀 Gemini Audio Video Chat Stream BOTH your webcam video and audio feeds to Google Gemini. You can also upload images to augment your conversation! Demo | Code	🗣️ Google Gemini Real Time Voice API Talk to Gemini in real time using Google's voice API. Demo | Code
🗣️ OpenAI Real Time Voice API Talk to ChatGPT in real time using OpenAI's voice API. Demo | Code	🤖 Hello Computer Say computer before asking your question! Demo | Code
🤖 Llama Code Editor Create and edit HTML pages with just your voice! Powered by SambaNova systems. Demo | Code	🗣️ Talk to Claude Use the Anthropic and Play.Ht APIs to have an audio conversation with Claude. Demo | Code
🎵 Whisper Transcription Have whisper transcribe your speech in real time! Demo | Code	📷 Yolov10 Object Detection Run the Yolov10 model on a user webcam stream in real time! Demo | Code
🗣️ Kyutai Moshi Kyutai's moshi is a novel speech-to-speech model for modeling human conversations. Demo | Code	🗣️ Hello Llama: Stop Word Detection A code editor built with Llama 3.3 70b that is triggered by the phrase "Hello Llama". Build a Siri-like coding assistant in 100 lines of code! Demo | Code

Usage

This is an shortened version of the official usage guide.

• .ui.launch(): Launch a built-in UI for easily testing and sharing your stream. Built with Gradio.
• .fastphone(): Get a free temporary phone number to call into your stream. Hugging Face token required.
• .mount(app): Mount the stream on a FastAPI app. Perfect for integrating with your already existing production system.

Quickstart

Echo Audio

from fastrtc import Stream, ReplyOnPause
import numpy as np

def echo(audio: tuple[int, np.ndarray]):
    # The function will be passed the audio until the user pauses
    # Implement any iterator that yields audio
    # See "LLM Voice Chat" for a more complete example
    yield audio

stream = Stream(
    handler=ReplyOnPause(echo),
    modality="audio", 
    mode="send-receive",
)

LLM Voice Chat

from fastrtc import (
    ReplyOnPause, AdditionalOutputs, Stream,
    audio_to_bytes, aggregate_bytes_to_16bit
)
import gradio as gr
from groq import Groq
import anthropic
from elevenlabs import ElevenLabs

groq_client = Groq()
claude_client = anthropic.Anthropic()
tts_client = ElevenLabs()


# See "Talk to Claude" in Cookbook for an example of how to keep 
# track of the chat history.
def response(
    audio: tuple[int, np.ndarray],
):
    prompt = groq_client.audio.transcriptions.create(
        file=("audio-file.mp3", audio_to_bytes(audio)),
        model="whisper-large-v3-turbo",
        response_format="verbose_json",
    ).text
    response = claude_client.messages.create(
        model="claude-3-5-haiku-20241022",
        max_tokens=512,
        messages=[{"role": "user", "content": prompt}],
    )
    response_text = " ".join(
        block.text
        for block in response.content
        if getattr(block, "type", None) == "text"
    )
    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)

stream = Stream(
    modality="audio",
    mode="send-receive",
    handler=ReplyOnPause(response),
)

Webcam Stream

from fastrtc import Stream
import numpy as np


def flip_vertically(image):
    return np.flip(image, axis=0)


stream = Stream(
    handler=flip_vertically,
    modality="video",
    mode="send-receive",
)

Object Detection

from fastrtc import Stream
import gradio as gr
import cv2
from huggingface_hub import hf_hub_download
from .inference import YOLOv10

model_file = hf_hub_download(
    repo_id="onnx-community/yolov10n", filename="onnx/model.onnx"
)

# git clone https://huggingface.co/spaces/fastrtc/object-detection
# for YOLOv10 implementation
model = YOLOv10(model_file)

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))

stream = Stream(
    handler=detection,
    modality="video", 
    mode="send-receive",
    additional_inputs=[
        gr.Slider(minimum=0, maximum=1, step=0.01, value=0.3)
    ]
)

Running the Stream

Run:

Gradio

stream.ui.launch()

Telephone (Audio Only)

```py
stream.fastphone()
```

FastAPI

app = FastAPI()
stream.mount(app)

# Optional: Add routes
@app.get("/")
async def _():
    return HTMLResponse(content=open("index.html").read())

# uvicorn app:app --host 0.0.0.0 --port 8000