MIT-licensed, DSH-native voice dictation plugin for the DeepSeek Harness web composer — offline-first via SenseVoice, with browser / cloud ASR fallback and an optional LLM polish step reusing your DSH model.
DSH integration
Native runtime
Author-claimed
Safety audit
Unaudited
Last verified
2026-09-06
License
MIT
01What can it help you accomplish?
Dictate text hands-free into the DeepSeek Harness web composer
Transcribed speech inserted at the composer cursor as editable text
DeepSeek Harness (dsh) web users who want voice-to-text input
Transcribe speech with the best available engine (offline-first)
Text via SenseVoice offline (audio never leaves the machine) or browser / cloud ASR fallback
Privacy-conscious dsh users and those behind restricted networks
02How to install into DeepSeek Harness
Installation steps
- 01
$ dsh plugin --profile web add dsh-voice-scribe # 重启 dsh web 后生效
Verify the integration
Not specified by the author
03DSH integration and capability boundaries
Installed via the official `dsh plugin --profile web add` command; injects voice dictation into the dsh web composer
Alt hotkey & microphone button dictation
Speech via microphone (tap/hold Alt, or click the 🎤 button)→Transcribed text inserted at the composer cursor
Multi-engine recognition (offline-first)
Microphone audio→Text via SenseVoice offline / browser Web Speech / cloud ASR service chain
First use auto-downloads the SenseVoice model (~230MB, one-time)Hold-to-talk mode
Hold the hotkey to record→Auto-transcribe on release
Hot-word replacement table
Edit $DSH_HOME/voice/hot.txt→Corrected transcription (literal + regex rules) applied to all engines
Optional LLM polish (reuses the DSH model)
Raw transcript + custom polish prompt→Cleaned text via local rule pre-polish then the DSH LLM
Polish prompt and transcript are sent to the DSH model
04Who is it for? When not to use it?
Good for
- DeepSeek Harness (dsh) web users who want voice-to-text input
- Privacy-conscious dsh users and those behind restricted networks
Not for
- Unofficial community plugin, not affiliated with DeepSeek / 深度求索; read SECURITY.md before use.
- Browser Web Speech relies on external services (Chrome is blocked in mainland China, Edge Stable has known regressions); local recognition is the default.
05Compatibility, maintenance and safety notes
- Unofficial community plugin, not affiliated with DeepSeek / 深度求索; read SECURITY.md before use.
- Browser Web Speech relies on external services (Chrome is blocked in mainland China, Edge Stable has known regressions); local recognition is the default.
- Maximum recording length is ~4 minutes on the local engine and 10 minutes on cloud ASR; recording auto-stops at the limit.
- The cloud ASR service chain requires configuring an API key in settings; the key is stored server-side only.
readme_verified
06Frequently asked questions
How do I install dsh-voice-scribe for DeepSeek Harness?
Run `dsh plugin --profile web add dsh-voice-scribe` in your terminal, then restart dsh web for the plugin to take effect. It is added as a web-profile plugin.
How do I start voice input?
Click the 🎤 microphone button next to the input box, or focus the input and press **Alt** to start talking and **Alt** again to stop and transcribe. **Alt+Space** is an alternative trigger you can switch in settings.
Does it work offline and stay private?
Yes by default. The local SenseVoice engine runs offline with zero config and zero API key, and audio never leaves your machine. Browser Web Speech and cloud ASR are opt-in fallbacks.
How do I fix mis-recognized words?
Edit the hot-word table at `$DSH_HOME/voice/hot.txt` (one rule per line). Literal `correct=wrong1|wrong2` and regex `/pattern/replacement/` rules are both supported and apply to all engines.
Is it an official DeepSeek plugin?
No. It is an unofficial community plugin and is not affiliated with DeepSeek / 深度求索. Read SECURITY.md before use.
07Related DSH workflows
vox-director
by alisa0808
Turn one topic into a finished Vox-style paper-collage explainer/ad video — automated end to end on Atlas Cloud + ffmpeg. An agent skill.
dsh-voice-ai-girlfriend
by beiyege-01
Voice AI girlfriend for DeepSeek Harness — Whisper voice input, voice cloning, streaming TTS and a digital-human avatar with interrupt mode.
dsh-plugin-tts
by 1624318455
Edge TTS voice plugin for DeepSeek Harness: read assistant replies aloud, auto-read toggle, voice settings panel (free, no API key)
dsh-speak
by alan2z
Make your DeepSeek Harness speak — voice announcements for agent activity.
08Data and sources
DSH 专属语音输入插件：**点按或按住 Alt 说话、松开/再点按转文字**，插入输入框光标处。
This page is generated from the project’s public documentation, repository metadata and a structured parse of DSH Plugins; last verified on 2026-09-06. Found an error? Submit a correction.
Best DeepSeek Harness Plugins
Twelve plugins worth installing first — picked from the whole catalog, across every category.