Back: Catalog

fastrtc

FastRTC is a library for creating real-time communication streams for Python. You can convert any Python function into real-time audio and video streaming via WebRTC or WebSocket protocols. The library includes components such as automatic voice detection, voice synthesis, built-in Gradio interface, and FastAPI integration.

FA

fastrtc

New80

gradio-app · Voice & Text-to-Speech

STARS4.6K
FORKS438
COMMITS0
CONTRIBUTORS0
VERSION0.0.34
UPDATED9 days ago
PythonWebRTCFastAPIGradioMIT

Common commercial products in this category: ElevenLabs, Amazon Polly, Google Cloud Text-to-Speech

What can it do?
  • Using WebRTC or WebSocket protocols, you can convert any Python function into real-time audio and video streaming.
  • You can manage speech streams with built-in voice sensing and text-reading features.
  • You can create endpoint for your own interface by connecting the stream to a FastAPI application.
Heads up
  • • Website is unreachable (checked: 2026-10-31)
User reviews
  • ↓ NegativeGitHub Issue

    VAD detects humming as speech

    “While using the `llm_voice_chat` demo, I hummed randomly, and the VAD model detected it as speech. However, the STT returned empty text, resulting in this: ![Image]( I tried setting `vad_options.threshold` to 0.7 but didn't see any changes. This seems more like a VAD model issue…”

  • • NeutralGitHub Issue

    Issues with aiortc state

    “Loosely speaking, chunks 1-5ish process well (200ms - 300ms latency as expected) but past that the server breaks. I ruled out the sttmodel being the issue (works over websockets). I believe its related to In my case I thought the instant emit may be flooding the event loop was a…”

GitHub

My note

Alternative pages

ElevenLabs alternativesAmazon Polly alternativesGoogle Cloud Text-to-Speech alternatives

More in: Voice & Text-to-Speech