dsh-hold-to-talk
One-handed, keyboard-free input for the composer: press and hold the mouse on the input box, speak, release — the text lands in the draft, and sliding up cancels without leaving a half sentence behind. No mic button to aim at and no shortcut to remember; the hand never has to leave the input area, which is the point when the other hand is busy. Recognition runs fully offline (SenseVoice via sherpa-onnx, no API key, audio never leaves the machine).
输入框上的单手、免键盘输入：鼠标在输入框按住、说话、松手，文字直接进草稿；上滑取消，不留半句。不用去瞄麦克风按钮，也不用记快捷键，手始终不用离开输入区——另一只手正忙的时候，这一点才是关键。识别完全在本机完成（SenseVoice + sherpa-onnx），无需 API key，音频不出本机。
How to install
dsh plugin add dsh-hold-to-talk About
dsh-hold-to-talk **Hold-to-talk voice input for the DeepSeek Harness Web composer** — the WeChat-desktop gesture: hold the mouse on the input box, speak, see the running transcript float above it, release to drop the text into the draft. Recognition runs **locally** (SenseVoice via sherpa-onnx): no API key, offline, audio never leaves the machine. **DSH Web 输入框的"长按说话"语音输入** —— 微信电脑版同款操作：在输入框上按住鼠标说话，浮层里边说边出字，松手把文字写进输入框，上滑取消。识别全部在**本机**跑（SenseVoice + sherpa-onnx），免密钥、离线、音频不出本机。 ┌─ composer ──────────────────────────────────┐ │ [hold the mouse, don't move, 400ms] │ │ ↓ │ │ ┌──────────────────────…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 3
- mo. downloads
- –
- Last push
- 2026-09-11
- Created
- 2026-09-11
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- asr, audio, deepseek-harness, dictation, dsh, dsh-plugin, hold-to-talk, local-first, nodejs, offline, plugin, privacy, push-to-talk, sensevoice, sherpa-onnx, speech-to-text, voice, voice-input, wechat, wechat-desktop
Related plugins
dsh-voice
GooDAnDReaDY/dsh-voice
Voice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).
dsh-omi-voice
PolinniZhong/dsh-omi-voice
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.
dsh-plugin-uisfx
XanthanL/dsh-plugin-uisfx
Semantic UI sound effects powered by uisfx: task start/success/failure and per-button cues, settings UI with instant preview, 12 sound packs, Host-persisted preferences, and `ctx.uisfx` service for other plugins.
dsh-gsv
TaoruiLiu19/dsh-gsv
Real-time local TTS for DeepSeek Harness: voice presets, auto-read, engine setup assistant, a read-aloud button, and a settings panel for the GSV-TTS-Lite engine.