dsh-speak
Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices) 适合需要听取AI回复、支持Windows和macOS系统语音的用户。
同名パッケージの別リポジトリ
インストール
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:Alan2Z/dsh-speakドキュメント
README 全文を読む ↗Configuration
Engine parameters
See docs/DESIGN.md §5 configuration reference:
speak.ps1 -Text "…" -Volume 50 -Rate 1 -MaxChars 300 -LongTextMessage "本次播报内容较长,请自行阅读。"
DSH plugin config
Either way works, and they stay in sync (both write the same settings document):
- Web UI (1.7.0, recommended): a dedicated Settings → dsh-speak settings
page. Every option is editable and saved there (visible in
dsh --dump-config, per-profile, survives npm updates). - Profile patch
configblock (equivalent):