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。

其他擴充

套件: dsh-voice-polish
相容性: 待驗證
Harness 依賴範圍: >=0.2.2-rc.1
Cordis 依賴範圍: >=4.0.1
版本: 1.0.0
授權: MIT
最近更新: 2026年11月10日

同名套件的其他儲存庫

molanxuan-del/DSH-VoxPolish

安裝

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

說明文件

閱讀完整 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