DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-voice

Voice input and real-time streaming dictation with multi-provider fallback chains for DeepSeek Harness.

UI & ProductivityDeveloper ToolsBrowser & Web
7GitHub Stars3ForksUpdated2026-09-21

Install

$ dsh plugin --profile web add @goodandready/dsh-voice

Plugin 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.

source-grounded
dsh-voice integrates voice input capabilities into the DeepSeek Harness Web UI and agent runtime. It provides real-time streaming dictation chunked by voice activity detection (VAD), tactile Push-to-Talk gestures, offline local whisper.cpp execution, and automated fallback chains across multiple cloud speech-to-text providers.

Key Capabilities

  • Streaming dictation segmented by voice activity detection (VAD)
  • Mouse and keyboard push-to-talk (PTT) audio messaging with customizable hotkeys and cancel windows
  • Multi-provider speech-to-text fallback chains (Deepgram, Groq, HuggingFace, OpenAI, local whisper.cpp, and compatible endpoints)
  • In-browser zero-latency speech recognition using Web Speech API
  • Offline whisper-server management with on-the-fly ffmpeg transcoding
  • Agent tool transcribe_audio for transcribing local audio files directly in chat flows

Useful For

  • Dictating long-form prompts or instructions into DeepSeek Harness hands-free
  • Sending quick voice messages to agents with mouse or keyboard push-to-talk gestures
  • Running fully offline, privacy-first audio transcription with local whisper.cpp
  • Enabling agents to transcribe stored interview recordings and voice files from disk

Who It Fits

  • DeepSeek Harness Web UI users seeking hands-free voice dictation
  • Developers needing reliable multi-provider fallback audio transcription
  • Privacy-focused users requiring local offline Whisper integration

Documented Limitations

  • Local Whisper integration requires whisper.cpp binaries and compatible GGML models installed locally
  • Audio transcoding relies on ffmpeg availability on the host backend
  • In-browser zero-latency captions rely on Web Speech API support (primarily Google Chrome)

DSH Compatibility

Version-specific runtime evidence collected by DSH Plugin. A missing result means we have not tested that combination yet.

Not tested yetNo runtime compatibility tests have been published yet.

Security Signals

Objective signals discovered from package metadata and source inspection. These are not a guarantee that a plugin is safe.

No automated security signals have been published yet.

Source & Registry Notes

Public provenance, Registry classification, and the latest source check for this entry, kept separate from runtime verification.

Source repository
GooDAnDReaDY/dsh-voice
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
7440685 · 2026-09-21

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
7GitHub stars
Forks
3
Open issues
0
Last commit
2026-09-21
Last release
2026-09-19
For maintainers

Maintaining this plugin?

This listing is generated from public repository data. If you maintain this project, you can review the information and share this listing with your users if you find it useful.

Add to README
Listed on DSHPlugin.app