dsh-voice
Web UI 全双工语音对话：点按切换或按住说话（发送键或 `Ctrl`）并显示实时字幕，宿主端 SenseVoice（sherpa-onnx）转写，回复按句流式朗读，开口说话即打断播放与正在运行的回合（真 barge-in），无需 API key。
Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.
怎么安装
dsh plugin add @haoku123/dsh-voice 简介
dsh-voice Full-duplex voice mode for DeepSeek Harness: streamed ASR → LLM → TTS with barge-in. Status **v0.5.0 — SenseVoice (sherpa-onnx) host-side ASR.** Speak into the composer mic: the assistant silences itself (playback stops, host synthesis queue drops), the running turn is cancelled (the stop-button route), and your speech is transcribed by the host (SenseVoice, CN-native simplified-Chinese ASR with punctuation + ITN) and submitted. The reply streams back as spoken audio with live captions. Known limitation: barge-in detection is triggered by the mic's leading speech edge, which relies o…
推荐参考
信息
- 协议
- MIT
- 语言
- TypeScript
- GitHub 星标
- 4
- 月下载
- 791
- 最近更新
- 2026-08-23
- 创建于
- 2026-08-15
基础安全检查
- 检查结果
- 无
- 收录来源
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- 主题标签
- asr, deepseek-harness, dsh, dsh-plugin, sensevoice, sherpa-onnx, tts, voice, voice-mode
同类推荐
dsh-voice-scribe
PensiveFei/dsh-voice-scribe
面向 Web UI 的语音输入插件：点按 Alt（或 Alt+空格）开始/停止听写，支持浏览器内置 Web Speech（零配置）或 OpenAI 兼容云端 ASR，可选经 DSH 已配置模型润色，带设置页。
dsh-tts
GooDAnDReaDY/dsh-tts
在 DeepSeek Harness 网页 UI 中朗读智能体回复，采用服务商回退链（OpenAI、ElevenLabs、Google、Azure、Groq、Deepgram、OpenRouter、Edge、Piper、eSpeak），某个服务商失败或被限流时自动切换到下一个，而不是直接静音。
dsh-ears
WizisCool/dsh-ears
面向 DeepSeek Harness (dsh) 的语音输入插件：输入框的麦克风按钮把语音转成草稿文本，支持多种语音识别后端，可选经 dsh 自有 LLM 路由润色，并带原生设置页。
dsh-omi-voice
PolinniZhong/dsh-omi-voice
DeepSeek Harness 对话内朗读：点一下即可朗读、暂停、继续 AI 回复，豆包 TTS 自然音色（BYOK），只读最终回答并过滤代码、表格与图形，本地引擎，插件零 Key。