Turn any python function into a real-time audio and video stream over WebRTC or WebSockets.
pip install fastrtcto 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]- 🗣️ 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
Streamcan 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.
See the Cookbook for examples of how to use the library.
|
Stream BOTH your webcam video and audio feeds to Google Gemini. You can also upload images to augment your conversation! gemini-audio-video-first.mp4 |
Talk to Gemini in real time using Google's voice API. gemini-live-chat.mp4 |
|
Talk to ChatGPT in real time using OpenAI's voice API. openai-live-chat.mp4 |
Say computer before asking your question! 2025-02-20_00-05-11.mp4 |
|
Create and edit HTML pages with just your voice! Powered by SambaNova systems. llama-code-editor.mp4 |
Use the Anthropic and Play.Ht APIs to have an audio conversation with Claude. talk-to-claude.mp4 |
|
Have whisper transcribe your speech in real time! whisper-realtime.mp4 |
Run the Yolov10 model on a user webcam stream in real time! yolov10-stream.mp4 |
|
Kyutai's moshi is a novel speech-to-speech model for modeling human conversations. talk-to-moshi.mp4 |
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! hey-llama-final.mp4 |
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.
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(detection),
modality="audio",
mode="send-receive",
)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),
)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",
)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)
]
)Run:
stream.ui.launch()```py
stream.fastphone()
```
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