mirror of
https://github.com/HumanAIGC-Engineering/gradio-webrtc.git
synced 2026-02-05 18:09:23 +08:00
853d6a06b5
* 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>
102 lines
3.0 KiB
Python
102 lines
3.0 KiB
Python
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)
|