dsh-voice-polish

Voice input with Feishu-style polish: local SenseVoice transcription, then DeepSeek tidies your spoken words into a ready-to-send draft. 对着电脑说话，本地转写，AI 把口语整理成通顺文字。

Other extensions

Package: dsh-voice-polish
Compatibility: Unverified
Harness peer range: >=0.2.2-rc.1
Cordis peer range: >=4.0.1
Version: 1.0.0
License: MIT
Last updated: Nov 10, 2026

Other repositories with this package name

molanxuan-del/DSH-VoxPolish

Install

npx -p @deepseek-ai/dsh dsh plugin --profile web add https://github.com/howie79794-sys/dsh-voice-polish/releases/download/v1.0.0/dsh-voice-polish-1.0.0.tgz

README

Read the full README ↗

Configuration

Edit the voice-polish row's config in your profile patch (toggle the plugin once to apply):

Field	Default	Notes
`language`	`auto`	Recognition hint: `auto` / `zh` / `en` / `yue` / `ja` / `ko`
`style`	`standard`	Tidy-up level: `light` / `standard` / `strict`
`polishProvider`	`deepseek-official`	Model route for tidying; falls back to a configured DeepSeek route automatically
`polishModel`	`deepseek-chat`	Model for tidying
`maxDurationSeconds`	`180`	Per-recording limit
`enabled`	`true`	Master switch