← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh

Wake-word voice input plugin for DeepSeek Harness using local SenseVoice STT to transcribe and auto-send prompts.

Developer ToolsRemote Execution
0GitHub Stars0ForksUpdated2026-10-27

Install

$ dsh plugin --profile desktop add github:AzhaI114514/dsh

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-fairy-wake is a voice input plugin for DeepSeek Harness that implements continuous microphone listening and wake-word detection for "你好Fairy" or "Fairy". Once triggered, it captures the subsequent speech, transcribes it locally using the official experimental SenseVoice STT service, and automatically submits the prompt to the active session by default.

Key Capabilities

  • Always-on microphone monitoring with energy-based Voice Activity Detection (VAD)
  • Wake-word trigger recognition for '你好Fairy' or 'Fairy' with error tolerance for common phonetic misspellings
  • Local speech-to-text transcription via Host CPU using SenseVoice
  • Direct prompt submission or draft insertion into the chat composer
  • Status indicator pill in the composer dock and dedicated settings configuration panel

Useful For

  • Hands-free voice interaction and prompt dispatching in DeepSeek Harness
  • Fairy desktop persona integration alongside complementary TTS and desktop skin plugins
  • Local offline voice input without requiring external cloud STT APIs

Who It Fits

  • DeepSeek Harness desktop users seeking hands-free voice control
  • Users running local offline speech transcription setups
  • Fairy desktop suite and persona enthusiasts

Documented Limitations

  • Requires DSH >=0.2.1-rc.1 and the official experimental voice-input bundle with SenseVoice (~240 MB)
  • Microphone stays continuously active and may conflict with other audio input sources or native buttons
  • Only activates in active conversation sessions, not on blank new session pages without an initial message
  • Uses segmentation and transcription-based wake-word matching rather than a dedicated low-power KWS engine

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.

Dependency Counts

package.json declares 0 runtime, 0 development, 0 peer, and 0 optional dependencies.

info
Dsh Bundle Declared

package.json declares DSH bundle metadata.

info
License Declared

GitHub reports the repository license as MIT.

info
Package Manifest Available

A root package.json was captured and can be inspected by the registry.

info
Source Available

Public GitHub source metadata is available for this registry snapshot.

info

Source & Registry Notes

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

Source repository
AzhaI114514/dsh
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
00e2fa9 · 2026-10-27

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
0GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-27
Last release
2026-10-27
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