Commit Graph

4 Commits

Author SHA1 Message Date
hailin 7fb0d1de95 refactor: remove Speechmatics STT integration entirely, default to OpenAI
- Delete speechmatics_stt.py plugin
- Remove speechmatics branch from voice-agent entrypoint
- Remove livekit-plugins-speechmatics dependency
- Change default stt_provider to 'openai' in entity, controller, and UI
- Remove SPEECHMATICS_API_KEY from docker-compose.yml
- Remove speechmatics option from web-admin settings dropdown

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-03 04:58:38 -08:00
hailin f9c47de04b feat: add STT provider switching (OpenAI ↔ Speechmatics) in settings
- Add VoiceConfig entity/repo/service/controller in agent-service
  for per-tenant STT provider persistence (default: speechmatics)
- Add Speechmatics STT plugin in voice-agent with livekit-plugins-speechmatics
- Modify voice-agent entrypoint for 3-way STT selection:
  metadata > agent-service config > env var fallback
- Add "Voice" section in web-admin settings page with STT provider dropdown
- Add i18n translations (en/zh) for voice settings
- Add SPEECHMATICS_API_KEY env var in docker-compose

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-02 22:13:18 -08:00
hailin 112c445143 fix: resolve websockets version conflict and use CPU-only torch
- Upgrade websockets from ==12.0 to >=13.0 (openai[realtime] requires >=13)
- Install torch CPU-only build separately in Dockerfile to avoid ~2GB CUDA download
- Remove torch from requirements.txt (installed via --index-url cpu wheel)

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 09:02:31 -08:00
hailin 94a14b3104 feat: migrate voice call from WebSocket/PCM to LiveKit WebRTC
实时语音对话架构迁移:WebSocket → LiveKit WebRTC

## 背景
原语音通话架构基于 FastAPI WebSocket 传输原始 PCM,管道串行执行
(VAD → 批量STT → Agent → 攒句 → 批量TTS),首音频延迟约 6 秒。
迁移到 LiveKit Agents 框架后,利用 WebRTC 传输 + 流水线并行,
预期延迟降至 1.5-2 秒。

## 架构
Flutter App ←── WebRTC (Opus/UDP) ──→ LiveKit Server ←──→ Voice Agent
  livekit_client                      (自部署, Go)       (Python, LiveKit Agents SDK)
                                                          ├─ VAD (Silero)
                                                          ├─ STT (faster-whisper / OpenAI)
                                                          ├─ LLM (自定义插件 → agent-service)
                                                          └─ TTS (Kokoro / OpenAI)

关键设计:LLM 不直接调用 Claude API,而是通过自定义插件代理到现有
agent-service,保留 Tool Use、会话历史、租户隔离等能力。

## 新增服务

### voice-agent (packages/services/voice-agent/)
LiveKit Agent Worker,包含:
- agent.py: 入口,prewarm() 预加载模型,entrypoint() 编排会话
- plugins/agent_llm.py: 自定义 LLM 插件,代理 agent-service API
  - POST /api/v1/agent/tasks 创建任务
  - WS /ws/agent 订阅流式事件 (stream_event)
  - 跨轮复用 session_id 保持对话上下文
- plugins/whisper_stt.py: 本地 faster-whisper STT (批量识别)
- plugins/kokoro_tts.py: 本地 Kokoro-82M TTS (24kHz PCM)
- config.py: pydantic-settings 配置

### LiveKit Server (deploy/docker/)
- livekit.yaml: 信令端口 7880, RTC TCP 7881, UDP 50000-50200
- docker-compose.yml: 新增 livekit-server + voice-agent 容器

### LiveKit Token 端点
- voice-service/src/api/livekit_token.py:
  POST /api/v1/voice/livekit/token
  生成 Room JWT,嵌入 auth_header 到 AgentDispatch metadata

## Flutter 客户端改造
- agent_call_page.dart: 从 ~814 行简化到 ~380 行
  - 替换: WebSocketChannel, AudioRecorder, PcmPlayer, 手动心跳/重连
  - 使用: Room.connect(), setMicrophoneEnabled(true), LiveKit 事件监听
  - 波形动画改用 participant.audioLevel
- pubspec.yaml: 添加 livekit_client: ^2.3.0
- app_config.dart: 增加 livekitUrl 字段
- api_endpoints.dart: 增加 livekitToken 端点

## 配置说明 (环境变量)
- STT_PROVIDER: local (默认, faster-whisper) / openai
- TTS_PROVIDER: local (默认, Kokoro) / openai
- WHISPER_MODEL: base (默认) / small / medium / large
- WHISPER_LANGUAGE: zh (默认)
- KOKORO_VOICE: zf_xiaoxiao (默认)
- DEVICE: cpu (默认) / cuda

## 不变的部分
- agent-service: 完全不改,voice-agent 通过现有 API 调用
- voice-service 核心: pipeline/STT/TTS/VAD 保留 (Twilio 备用)
- Kong 网关: 现有路由不变
- 数据库: 无 schema 变更

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 08:55:33 -08:00