← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-live-voice

Local-first voice interaction plugin for DeepSeek Harness providing STT, TTS, and meeting transcription.

Developer ToolsBrowser & WebRemote Execution
6GitHub Stars0ForksUpdated2026-10-25

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-live-voice is an installable DeepSeek Harness web plugin that enables voice-driven conversations, hands-free dialogue, speech synthesis, and real-time meeting transcription. It supports local browser-based models (such as Whisper and Qwen3-ASR) as well as external HTTP speech services, complete with a dedicated speech bar, playback controls, and acoustic isolation modes.

Key Capabilities

  • Voice typing into the DSH composer without overwriting manual text edits
  • Continuous hands-free dialogue and push-to-talk voice input
  • Narration of assistant responses and structured prompt questions
  • Real-time meeting audio capture and transcription via tab sharing or microphone
  • Dedicated playback speech bar with approximate captions, highlight tracking, and navigation controls
  • Support for local in-browser ASR (Whisper, Qwen3-ASR WebGPU/Wasm) and custom HTTP STT/TTS endpoints
  • Optional local audio session retention and retranscription using WebCodecs and IndexedDB

Useful For

  • Hands-free dictation and spoken interaction with the DeepSeek assistant
  • Listening to assistant answers while reviewing code or working across other windows
  • Transcribing live meetings to ask the assistant immediate contextual questions or summaries

Who It Fits

  • DSH users who prefer voice input and spoken output
  • Developers and professionals conducting code reviews or live meetings who need instant AI assistance

Documented Limitations

  • Not a native integration for Google Meet or Microsoft Teams; meeting audio capture requires separate browser tab sharing or external bridge setup
  • In-browser models require substantial initial downloads (up to 762 MB) and WebGPU/Wasm support
  • Persistent recording features depend on browser WebCodecs Opus, IndexedDB, and Web Locks support

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, 12 development, 0 peer, and 0 optional dependencies.

info
License Declared

GitHub reports the repository license as Apache-2.0.

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
wads-dev/dsh-live-voice
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
7862462 · 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
6GitHub stars
Forks
0
Open issues
1
Last commit
2026-10-25
Last release
2026-10-17
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