← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-voice

Voice input plugin for DeepSeek Harness web UI featuring streaming speech-to-text and offline dual-engine ASR.

UI & ProductivityBrowser & Web
8GitHub Stars0ForksUpdated2026-10-01

Install

$ dsh plugin --profile web add @nn12138/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 is an input-only speech recognition plugin for DeepSeek Harness web interface. It introduces a microphone button and customizable hotkey (Ctrl+Space by default) into the chat composer, capturing speech and submitting transcribed text as standard chat messages without modifying agent presets or personas. It operates an adaptive dual engine using host-native sherpa-onnx (zipformer2 with Silero VAD) for offline processing alongside automatic fallback to browser Web Speech API.

Key Capabilities

  • Adds microphone button and global hotkey triggering speech input in the DSH web UI composer
  • Provides real-time streaming recognition with live partial transcripts echoed during speech
  • Adaptive dual-engine operation supporting offline host-native ASR (sherpa-onnx) or browser Web Speech API fallback
  • Tail-padding and Silero VAD segmentation to prevent clipping at sentence boundaries
  • Submits transcribed text strictly as standard chat inputs without altering agent system prompts or presets

Useful For

  • Dictating prompts and instructions directly into DeepSeek Harness hands-free
  • Private, offline voice typing in local environments using native ONNX models
  • Rapid input across custom, minimal, or standard presets without reconfiguring personas

Who It Fits

  • DeepSeek Harness web UI users who prefer speech-to-text dictation
  • Developers seeking private, offline ASR without sending audio to third-party APIs
  • Accessibility-focused users needing hotkey and voice-driven prompt submission

Documented Limitations

  • Input-only; does not provide text-to-speech (TTS) or voice responses from the model
  • Host-native offline ASR requires optional peer dependency sherpa-onnx-node and manual model download via dsh-voice-models CLI
  • Engine requires web profile integration and platform client injection 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 1 runtime, 8 development, 1 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
3274375092/dsh-voice
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
de3911b · 2026-10-09

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
8GitHub stars
Forks
0
Open issues
0
Last commit
2026-10-01
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