DSH 全双工语音插件：流式语音识别入草稿、语音合成按句朗读 + 实时字幕、开口即打断；本地识别免 API Key，可选唤醒词。 · Full-duplex voice plugin for DeepSeek Harness: streaming speech-to-text into an editable draft, text-to-speech read-aloud with live captions, true barge-in and wake word; on-device ASR, no API key.
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.
Offline voice assistant for dsh web — wake word, speech dictation, voice edit commands & Chinese TTS. On-device sherpa-onnx WASM ASR, no Google dependency, works in China.
Hold-to-talk voice input for the DeepSeek Harness web composer: hold the mouse on the input box, speak, release to insert the text into the draft. Local SenseVoice ASR via sherpa-onnx: no API key, offline, audio never leaves the machine. | DSH 长按说话语音输入插件:输入框上按住鼠标说话,浮层边说边出字,松手把文字写进输入框,上滑取消;识别在本机跑,免密钥、离线、音频不出本机。
LLM Wiki workbench for dsh-better-sidebar: browse and lint a Karpathy-style interlinked markdown wiki, open pages with the native markdown viewer, clickable [[wikilinks]] and provenance/relative .md links, and backlinks. Ships the llm-wiki agent skill.
