sensevoice 6

Full-duplex voice plugin for DeepSeek Harness: local zipformer2 streaming ASR (no API key) → editable draft; Edge TTS or local VITS / Kokoro read-aloud with live captions; true barge-in; hardened HTTP surface + model SHA256 pinning; compatible with all ds

Hold-to-talk voice input for the DeepSeek Harness Web composer: hold the mouse on the input box, speak, see the running transcript float above it, release to insert the text into the draft. Recognition runs locally (SenseVoice via sherpa-onnx) — no API ke

个人语音通话助手（DSH 桌面端与 Web GUI 通用，profile 换成 desktop/web 即可）：专属工作区/会话（自动创建、跨重启保持）、悬浮球通话面板、本地 SenseVoice 语音识别（复用 DSH 语音输入插件已下载的模型，免装模型）/ FunASR 流式/HTTP、云端 TTS 语音回复（MiniMax / MiMo-V2.5-TTS 含导演模式 / OpenAI 兼容）、唤醒词通话模式（可配置唤醒词/休眠时长，建议本地 ASR）、子代理任务分发与进度跟踪。持久化安装，重启后仍在

Context-aware voice input for DeepSeek Harness with Web Speech, local SenseVoice transcription, model polish, editable Composer drafts, and user-controlled sending

SenseVoiceSmall-powered local speech-to-text for the DSH Desktop input box: click the mic beside the composer, speak, and the recognized draft (with language/emotion tags) is written into the input.

SenseVoice 语音输入插件 for DeepSeek Harness：在对话输入框旁添加麦克风按钮，录音后调用本地 SenseVoice 服务转成文本填入输入框。首次使用自动下载模型并显示进度，后端由插件自动启动。