← DeepSeek Harness Plugins
DeepSeek Harness PluginManifest Valid

dsh-dictate

Context-aware dictation and voice input for the DeepSeek Harness Composer with Web Speech and local SenseVoice support.

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 the DeepSeek Harness Composer toolbar. It supports zero-configuration Web Speech transcription as well as an optional local SenseVoice ASR engine on Apple Silicon macOS and Windows x64. The plugin extracts context-relevant vocabulary from the active session, supports optional LLM-driven polishing, and keeps draft editing and message sending strictly under user control.

Key Capabilities

  • Native DeepSeek Harness Composer toolbar integration for direct voice transcription
  • Zero-configuration live transcription using browser Web Speech API in Chrome and Edge
  • Optional local SenseVoice ASR backend for offline speech-to-text without WASM overhead
  • Session-aware vocabulary extraction and LLM-powered transcript polishing
  • Configurable keyboard shortcuts (Right Command / Right Control) and hold-to-speak mouse triggers
  • User-controlled review workflow with optional auto-send upon explicit user stop

Useful For

  • Dictating prompts and multi-turn instructions into DeepSeek Harness hands-free
  • Improving recognition of specialized technical terms and mixed Chinese/English vocabulary from session context
  • Polishing spoken drafts automatically using the active model before manual review or submission

Who It Fits

  • DeepSeek Harness users who prefer voice input and dictation over typing
  • Developers and researchers operating in bilingual Chinese and English workflows
  • Users needing offline local speech recognition on Apple Silicon macOS or Windows x64

Documented Limitations

  • Does not provide two-way conversational voice dialog or text-to-speech (TTS) playback
  • Bundled local ASR binaries currently support macOS Apple Silicon and Windows x64 only; Linux, Windows ARM64, and macOS Intel must use Web Speech
  • Windows local ASR binary is unsigned and runs in a visible console window
  • Auxiliary model calls for vocabulary extraction and polishing are not logged to DSH session history

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, 28 development, 13 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
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
11
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