1cd2da1042ce3741088e7424f8395ef44eb7fbbc
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
使用 agent profile(推荐)
python -m app.main --agent-profile default
使用指定 YAML
python -m app.main --agent-config config/agents/default.yaml
Agent 配置路径优先级
--agent-config--agent-profile(映射到config/agents/<profile>.yaml)AGENT_CONFIG_PATHAGENT_PROFILEconfig/agents/default.yaml(若存在)
说明
- Agent 相关配置是严格模式:YAML 缺少必须项会直接报错,不会回退到
.env或代码默认值。 - 如果要引用环境变量,请在 YAML 显式写
${ENV_VAR}。 siliconflow独立 section 已移除;请在agent.llm / agent.tts / agent.asr内通过provider、api_key、api_url、model配置。
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 docs/ws_v1_schema.md.
Description
Languages
Python
100%