wx44wx/ai-video-fullstack
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat(qwen-audio): add Alibaba Cloud Qwen-Audio Realtime service integration

Browse Source 
- Introduced Qwen-Audio Realtime service for speech-to-speech processing in Pipecat.
- Updated interface catalog to include Qwen-Audio Realtime capabilities.
- Enhanced model resource testing to support new service.
- Added configuration options for audio sample rates and turn detection modes.
- Updated documentation to reflect integration details and usage instructions.
This commit is contained in:
Xin Wang
2026-07-21 15:57:43 +08:00
parent f027ed99b7
commit 774825593d
10 changed files with 866 additions and 19 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
backend/README.md
View File

@@ -184,5 +184,6 @@ HTTP 工具可通过“响应变量赋值”把 JSON 路径写回普通会话变
- [ ] 联调 Pipecat 1.3.0 语音链路与各 OpenAI 兼容服务
- [ ] 起本地 SenseVoice / CosyVoice 的 OpenAI 兼容服务
- [x] `realtime` 模式(StepFun StepAudio Realtime)
- [x] `realtime` 模式(Alibaba Cloud Qwen-Audio 3.0 Realtime MVP)
- [x] 前端 `DebugVoicePanel` 接 `/ws/voice`(参考 dograh `useWebSocketRTC.tsx`)
- [ ] 加 DB 后:助手配置入库(目前随请求内联)