Files
AI-VideoAssistant/engine
2026-02-12 15:44:01 +08:00
..
2026-02-11 11:39:45 +08:00
2026-02-12 15:44:01 +08:00
2026-02-11 09:50:46 +08:00
2026-02-10 16:28:20 +08:00
2026-02-10 16:28:20 +08:00
2026-02-12 15:39:09 +08:00

py-active-call-cc

Python Active-Call: real-time audio streaming with WebSocket and WebRTC.

This repo contains a Python 3.11+ codebase for building low-latency voice pipelines (capture, stream, and process audio) using WebRTC and WebSockets. It is currently in an early, experimental stage.

Usage

启动

uvicorn app.main:app --reload --host 0.0.0.0 --port 8000

测试

python examples/test_websocket.py
python mic_client.py

WS Protocol

/ws uses a strict v1 JSON control protocol with binary PCM audio frames.

See /Users/wx44wx/.codex/worktrees/d817/AI-VideoAssistant/engine/docs/ws_v1_schema.md.