dsh-hold-to-talk

DeepSeek Harness 其他低风险

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。

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).

怎么安装

DeepSeek Harness dsh plugin add dsh-hold-to-talk

简介

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] │ │ ↓ │ │ ┌──────────────────────…

GitHub ↗

信息

协议: MIT
语言: JavaScript
GitHub 星标: 3
月下载: –
最近更新: 2026-09-11
创建于: 2026-09-11

链接

GitHub ↗ npm ↗ 报告问题 ↗

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, 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

dsh-hold-to-talk

怎么安装

简介

推荐参考

信息

链接

基础安全检查

同类推荐

dsh-voice

dsh-omi-voice

dsh-plugin-uisfx

dsh-gsv