← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dshtools-sensevoice-input

Local speech-to-text input plugin for DSH Desktop powered by SenseVoiceSmall.

UI & ProductivityTerminal & TUIDeveloper ToolsSkills & Workflows
1GitHub Stars0ForksUpdated2026-09-03

Install

$ dsh plugin --profile desktop add dshtools-sensevoice-input

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
dshtools-sensevoice-input is a voice input plugin for DSH Desktop that embeds a microphone button next to the composer. It performs offline speech-to-text inference locally using SenseVoiceSmall via funasr, automatically inserting transcribed text and language or emotion tags into the prompt input box without sending audio to external cloud services.

Key Capabilities

  • Embeds a dedicated microphone recording button into the DSH Desktop composer UI
  • Transcribes local audio via SenseVoiceSmall and auto-fills recognized text into the input draft
  • Parses and displays multi-lingual and emotional tags alongside transcribed text
  • Performs 100% offline local inference on CPU with process auto-recovery
  • Adapts UI styling automatically to match light and dark application themes

Useful For

  • Dictating long prompts or chat queries directly into DSH Desktop without typing
  • Multi-lingual voice drafting with automatic emotion and language tagging
  • Air-gapped or privacy-sensitive desktop environments where audio data must stay local

Who It Fits

  • DSH Desktop users who prefer speech input over manual typing
  • Developers and prompt engineers operating in offline or privacy-conscious environments
  • Multi-lingual users requiring fast local voice transcription

Documented Limitations

  • Operates as offline batch recognition rather than real-time streaming
  • Limits single-segment voice recording length to 60 seconds
  • Initial CPU model loading takes approximately 10 to 30 seconds before subsequent fast inference
  • Requires a local Python 3.12 environment with funasr, PyTorch, and approximately 5GB model storage

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, 6 development, 5 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
ilovedyou6666-hub/dshtools-sensevoice-input
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
f88b0a5 · 2026-09-06

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
1GitHub stars
Forks
0
Open issues
0
Last commit
2026-09-03
Last release
2026-09-03
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