← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-voice-mini

Voice-feedback plugin for DeepSeek Harness with model speech tools, verbalizers, and multi-backend TTS.

UI & ProductivityDeveloper ToolsBrowser & WebSecurity & Policy
1GitHub Stars0ForksUpdated2026-10-13

Install

No clear install command was found in the current repository evidence.

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-mini is an audio feedback plugin for DeepSeek Harness Desktop. It allows the assistant to speak brief updates and decisions using its own voice or fallback templates, provides per-session voice distinctness, audio chimes, verbalizer rewriting, performance monitoring, and an optional native macOS floating status widget.

Key Capabilities

  • Provides a speak tool for model-directed audio feedback and status updates
  • Supports multiple TTS backends including Microsoft Edge TTS, local Kokoro-82M, and macOS say
  • Automatic per-session voice assignment with jitter and customizable voice palettes
  • LLM verbalizer pass for sentence-by-sentence spoken summaries with emotional framing
  • Configurable earcons and chimes for notifications and quiet-mode alerts
  • Built-in metrics monitoring panel and optional macOS native floating pet widget
  • Full Chinese and English internationalization for UI and spoken phrases

Useful For

  • Listening to execution progress and task completion alerts without watching the screen
  • Receiving audio prompts for user approval or blocking questions during agent workflows
  • Differentiating multiple concurrent DeepSeek Harness sessions using unique voice assignments

Who It Fits

  • Developers and power users running long DeepSeek Harness workflows who prefer audio notifications
  • Accessibility-focused users wanting audible cues and summaries in DeepSeek Harness

Documented Limitations

  • Local Kokoro TTS backend only supports English
  • Native floating pet widget is designed specifically for macOS (Swift NSPanel)
  • Edge TTS backend requires internet connectivity to access cloud neural voices

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 2 runtime, 8 development, 2 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
CroissanTTs/dsh-voice-mini
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
281f2a0 · 2026-10-18

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
2026-10-13
Last release
No release detected
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