2026-02-25 15:52:55 +08:00
2026-02-25 15:52:55 +08:00
2026-02-25 15:52:55 +08:00
2026-02-25 15:52:55 +08:00
2026-02-25 10:08:19 +08:00
2026-02-25 15:52:55 +08:00
2026-02-23 17:16:18 +08:00
2026-02-24 05:55:47 +08:00
2026-02-17 10:39:23 +08:00
2026-02-17 10:39:23 +08:00
2026-02-25 15:52:55 +08:00
2026-02-25 15:52:55 +08:00
2026-02-17 10:39:23 +08:00
2026-02-25 15:52:55 +08:00
2026-02-17 10:39:23 +08:00
2026-02-17 10:39:23 +08:00
2026-02-25 15:52:55 +08:00
2026-02-25 15:52:55 +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

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

  1. --agent-config
  2. --agent-profile(映射到 config/agents/<profile>.yaml
  3. AGENT_CONFIG_PATH
  4. AGENT_PROFILE
  5. config/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 providerapi_keyapi_urlmodel 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
No description provided
Readme 2.8 MiB
Languages
Python 100%