dsh-voice-mode
Full-duplex voice conversation plugin for DeepSeek Harness with streaming local STT, TTS read-aloud, and barge-in interruption.
Install
$ dsh plugin --profile web add dsh-voice-modePlugin Overview & Capabilities
AI-assisted organization based on the public repository snapshot. The content must be grounded in source evidence and does not replace compatibility or security verification.
Key Capabilities
- Streaming speech-to-text with zipformer2 and SenseVoice punctuation and ITN
- Sentence-by-sentence text-to-speech read-aloud via Edge TTS or on-device VITS/Kokoro
- Real-time synchronized live subtitle overlays with adjustable font sizes and widths
- Conversational barge-in interruption and short backchannel yielding
- Hands-free automatic sending and push-to-talk microphone gestures with Ctrl+Shift+V shortcut
Useful For
- Conducting hands-free conversational chats in DeepSeek Harness sessions
- Dictating drafts and queries directly into the composer without cloud speech API keys
- Listening to long model responses with live subtitle tracking and instant voice interruption
Who It Fits
- DeepSeek Harness users seeking hands-free voice interactions
- Privacy-focused developers requiring local offline ASR or TTS pipelines
- Users needing accessible captions and auditory feedback for AI responses
Documented Limitations
- Default Ctrl+Shift+V keyboard shortcut overrides standard browser plain text paste
- Safari and iOS require HTTPS or localhost and suspend recognition/audio in background or lock screen
- Default Edge TTS depends on Microsoft online service availability
- Local ASR and VITS/Kokoro models require downloading model files on first launch
DSH Compatibility
Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.
Security Signals
Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.
GitHub reports the repository license as MIT.
No root package.json was captured in the latest GitHub snapshot.
Public GitHub source metadata is available for this registry snapshot.
Source & Registry Notes
Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.
- Source repository
- qishuilalala/dsh-voice-mode
- Registry source
- GitHub · dsh-plugin topic
- Registry classification
- Plugin
- Source checked
- 78200ec · 2026-10-19
This project is independently indexed from public source information. DSH Plugin is not affiliated with DeepSeek or the plugin author. Always check the author repository before installation.
Repository Activity
- GitHub stars
- 19GitHub stars
- Forks
- 5
- Open issues
- 1
- Last commit
- 2026-10-19
- Last release
- 2026-10-19
Related DSH Plugins
Ranked by overlapping capabilities, use cases, plugin type, categories, and DSH profile.
Theme, wallpaper, and styling plugin for DeepSeek Harness with 8 preset themes, glassmorphism, accent colors, and custom theme packs.
View plugin →Skill manager UI for DeepSeek Harness to discover, toggle, import, and update agent skills.
View plugin →Use ChatGPT, Claude, Grok, GitHub Copilot, and Antigravity subscriptions as DeepSeek Harness LLM providers via OAuth.
View plugin →Full office suite integration for DeepSeek Harness supporting spreadsheets, docs, slides, bases, and canvases.
View plugin →