DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-dictate

Context-aware dictation plugin for DeepSeek Harness with Web Speech and local SenseVoice transcription directly in Composer.

Developer Tools
1GitHub Stars0ForksUpdated2026-09-07

Install

$ dsh plugin --profile web add dsh-dictate@latest

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-dictate embeds context-aware speech-to-text directly into DeepSeek Harness Composer. It offers instant zero-config transcription via browser Web Speech API as well as an optional local SenseVoice ASR runtime on Apple Silicon, featuring session-aware vocabulary extraction, optional LLM polishing, and strictly user-controlled submission.

Key Capabilities

  • Native Composer toolbar integration displaying real-time transcription status directly in the input box
  • Dual transcription pipelines: zero-config Web Speech API or local loopback SenseVoice ASR
  • Session and Composer context extraction for improved mixed-language recognition and terminology weighting
  • Optional LLM-based draft polishing using the active DeepSeek session context before writing back to Composer
  • Keyboard shortcut trigger (right Command on macOS / right Control on Windows & Linux) when Composer is focused
  • Self-contained local ASR management on Apple Silicon Mac with progress tracking, model verification, and auto-start

Useful For

  • Dictating long-form prompts, instructions, and queries into DeepSeek Harness without typing
  • Transcribing mixed Chinese-English technical terminology accurately with context-assisted phrasing
  • Running completely local, offline-capable speech recognition on Apple Silicon hardware
  • Drafting and refining spoken inputs with LLM polishing before submitting to conversational sessions

Who It Fits

  • DeepSeek Harness users seeking hands-free or voice-first prompt entry
  • Developers and writers dictating technical terminology requiring context-aware recognition
  • macOS Apple Silicon users wanting local, privacy-preserving voice transcription without external API keys

Documented Limitations

  • Local SenseVoice one-click runtime and installation currently supports only macOS Apple Silicon (ARM64)
  • Web Speech mode requires Chrome or Edge browser support and active microphone permissions
  • Local ASR transcribes upon stopping and does not provide real-time streaming interim text
  • Helper model calls for vocabulary extraction and polishing do not write to DSH session event logs

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.

No automated security signals have been published yet.

Source & Registry Notes

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

Source repository
franksong2702/dsh-dictate
Registry source
GitHub · dsh-plugin topic
Registry classification
Plugin
Source checked
74ef255 · 2026-09-18

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
3
Last commit
2026-09-07
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