[Add Plugin] GooDAnDReaDY/dsh-voice

[GooDAnDReaDY]

Plugin name

GooDAnDReaDY/dsh-voice

Repository URL

https://github.com/GooDAnDReaDY/dsh-voice

Install identifier

@goodandready/dsh-voice

Category

Tools & Data / Media Tools

Category evidence

• Manifest: package.json — declares dsh.bundle.patch: ./cordis.patch.yml.
• Patch: cordis.patch.yml — the loader entry, named @goodandready/dsh-voice to match the npm package.
• README: README.md — installation and usage.
• npm: https://www.npmjs.com/package/@goodandready/dsh-voice

Summary

Voice input for the DeepSeek Harness web UI: dictation chunked by pauses plus voice messages, each with its own speech-to-text provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or any OpenAI-compatible endpoint). Recording and transcription happen in the composer, so the text can be edited before it is sent.

Install: dsh plugin --profile web add @goodandready/dsh-voice

Maintainer identity

GooDAnDReaDY

Submission declaration

• I maintain this plugin or have permission to submit it.
• The repository is public and the information above is accurate to the best of my knowledge.
• The root package.json declares dsh.bundle and the README includes installation or usage guidance.
• This request contains exactly one plugin.

[github-actions]

录入检查已完成，PR 正在处理：#147

Admission review is complete. The PR is in progress: #147