# gradio-app/fastrtc

The python library for real-time communication

Repository: https://github.com/gradio-app/fastrtc
Canonical: https://ross.abutalabs.com/products/fastrtc
Homepage: https://fastrtc.org/
Language: JavaScript
License: MIT
License Family: permissive
Topics: artificial-intelligence, llm, python, real-time, speech-to-text, text-to-speech, hacktoberfest, hacktoberfest2025
Last push: 2026-01-12T15:53:57+00:00

## Health v2 (maintenance only)
Score: 58/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 62, release rhythm 58, longevity 50
- inputs: {"age_days": 707, "days_push": 233, "days_rel": 282, "gap_med": 6, "n_releases_24m": 22}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4622, forks 433 (observed 2026-08-28T04:08:55.167068+00:00)

## What it is
FastRTC is a Python library that turns any Python function into a real-time audio and video stream over WebRTC or WebSockets. It includes built-in voice activity detection, turn-taking, an auto-launched Gradio UI, and easy mounting on FastAPI apps for custom frontends.

## Use cases
- build a real-time voice chatbot with an LLM
- stream webcam audio and video to a multimodal AI model
- add speech-to-text and text-to-speech to a Python app
- create a phone-callable voice assistant
- mount a WebRTC endpoint on a FastAPI backend
- prototype voice agents with automatic pause detection

## When to choose
- you want to build real-time audio/video AI applications in Python with minimal boilerplate
- you need built-in voice detection, turn-taking, and TTS/VAD extras
- you want a quick Gradio UI plus the option to mount on FastAPI for production

## When to avoid
- you need a non-Python stack or fine-grained low-level WebRTC control
- your use case is offline batch audio/video processing rather than live streaming
- you need production telephony features beyond the temporary free phone number

## Facets
- artifact type: library
- maturity: active
- function: audio-processing, speech-recognition, tts, websocket, http-server, llm-inference, chatbot
- domain: artificial-intelligence, large-language-models, speech-processing, web-development
- platform: python, cross-platform
- tags: webrtc, real-time-communication, voice-agents, voice-activity-detection, gradio, fastapi, streaming-audio, streaming-video, audio, video, real-time, web-server

## Member repositories
- gradio-app/fastrtc (main) score 58

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:55.167068+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:19:39.086690+00:00, confidence not recorded.
  - readme: https://github.com/gradio-app/fastrtc (fetched 2026-08-28T04:08:55.167068+00:00, sha 8a0436671032)
- Data as of 2026-08-30T08:39:29.467469+00:00.