gradio-app

FastRTC: Build Real-Time Audio and Video Streams in Python

FastRTC is a Python library for turning functions into real-time audio and video streams over WebRTC or WebSockets. It provides Gradio testing interfaces and FastAPI integration for building interactive voice, video, and AI applications.

ActiveJavaScriptMITPythonLibraryReal Time
Stars
4.6k
Forks
437
Stars, last 30 days
+6
Last commit
today
Contributors
36

Our take

Activerecent releases

Health score

39/100

How it is scored
Activity
41
Community
51
Issues
21
Pull requests
43

+6 stars in the last 30 days

FastRTC is a focused way to connect Python application logic to live media, with recent signs of maintenance but development concentrated among a small share of contributors.

Good fit if

  • Your application is Python-based and needs audio or video streaming over WebRTC or WebSockets.
  • You want a built-in Gradio UI for prototyping or a FastAPI mount point for integration.
  • You are comfortable evaluating a project where one contributor accounts for most recorded contributions, despite a broader contributor base and recent release activity.

Look elsewhere if

  • You need a non-Python streaming framework, or your runtime cannot meet the Python version requirement.
  • You need evidence of consistently rapid issue resolution: no issues were closed in the recent measurement period.
  • Your project requires contributions to be broadly distributed across maintainers.
All health signals
Last commit2026-10-21 (today)
Commits, last 90 days1
Releases, last 12 months1 (latest 0.0.34, 2025-11-24)
Contributors36 (top contributor: 77% of commits)
Issues closed, last 90 days0
Pull requests merged, last 90 days1
Project age2 years

Checked on 2026-10-22 with the GitHub API.

Project history

Daily GitHub snapshots since Oct 7, 2026. History covers stars and forks; health signals are not tracked historically.

Selected snapshot

Stars

4,637

Forks

439

Change since Nov 14, 2026: 0 stars·0 forks

Overview

FastRTC is a Python library for turning Python functions into real-time audio and video streams over WebRTC or WebSockets. It addresses the integration work involved in receiving live media, processing it with application logic, and returning responses, with built-in support for Gradio interfaces and FastAPI deployment.

It is aimed at Python developers building interactive media experiences, including speech-driven AI applications. You can start with a simple audio or video handler, then connect services such as transcription, language models, or text-to-speech as needed.

Key Features

  • Stream audio or video through WebRTC or WebSockets.
  • Wrap application logic in a Stream handler for sending and receiving media.
  • Use ReplyOnPause for audio turn-taking based on pauses.
  • Launch a built-in Gradio interface with .ui.launch().
  • Mount streams on a FastAPI app with .mount(app) for custom frontend integration.
  • Add optional voice activity detection and text-to-speech dependencies with the vad and tts extras.
  • Start an audio-only telephone interface with .fastphone().

Use Cases

  • Build a voice assistant that transcribes a user's speech, calls an LLM, and speaks the response.
  • Prototype speech-to-text or text-to-speech interactions with a built-in Gradio interface.
  • Process a live webcam feed for tasks such as object detection or image transformations.
  • Add real-time audio or video endpoints to an existing FastAPI application.

What you need

Detected in the repository

  • Python >=3.10 (from pyproject.toml)
  • A test suite and automated checks on GitHub Actions

License in plain words

MITpermissive

  • Commercial use: yes
  • Modify and redistribute: yes
  • You must keep: the copyright and license notice
  • Share your changes: no

A summary, not legal advice: the LICENSE file is what applies.

Getting Started

Install FastRTC with pip:

pip install fastrtc

For built-in pause detection and text-to-speech, install the optional extras:

pip install "fastrtc[vad, tts]"

See the README and documentation for setup and usage details.

Alternatives

  • xiaozhi-esp32-server: xiaozhi-esp32-server is a self-hosted backend for voice-enabled ESP32 devices, while FastRTC is a Python library for building real-time audio and video apps.
ProjectLanguageLicenseStarsStatus
FastRTCJavaScriptMIT4.6kActive
xiaozhi-esp32-serverJavaScriptMIT10.7kActive

Considerations

FastRTC requires Python 3.10 or newer. Its README describes optional dependencies for voice activity detection and text-to-speech; teams should check those extras against their deployment environment. The project is active and has had a recent release, but measured recent commit activity is limited, most contributions come from one person, and no issues were closed during the recent measurement period. The MIT license is permissive, but adopters should retain required copyright and license notices.

Found this useful?

Share it with someone who would like FastRTC.

Comparisons