DSH Plugin Hub
English | 中文

haoku123/dsh-voice

Plugin ⭐ 0 MIT other

Full-duplex voice plugin for DeepSeek Harness: mic → SenseVoice ASR (sherpa-onnx) → LLM → Edge TTS with true barge-in. 全双工语音插件：麦克风语音输入，SenseVoice 本地识别（简体中文+标点+ITN），流式 TTS 朗读，支持语音打断。Zero API key.

↗ View on GitHub 📄 Read full README

Install

input:  mic ──RMS endpoint detection──▶ POST /asr (raw f32 PCM)
                                           │ text (SenseVoice)
                                           ▼
        composer draft ──submit──▶ model stream ──llm/stream tap──▶ SentenceSegmenter
                                                                     │
        browser ◀── SSE /dsh-voice-api/stream ── TtsQueue (msedge-tts) ◀──┘
                  (base64 MP3 frames + caption text)

barge-in: speech edge ──▶ engine.skip() + POST /cancel (epoch bump)
                         + session.cancel() when a turn is running

Add haoku123/dsh-voice to your DSH config (web profile) to enable.

README

4.9 KB · Cached 2026-08-18 17:12:13 · 4.9 KB
Expand full README Collapse

README is empty.

Rendered from README.md of haoku123/dsh-voice. View original on GitHub →

Related Plugins