Editable local and desktop dictation for DeepSeek Harness
- 版本
- v0.1.0-beta.1
- 许可证
- MIT
- 收录日期
- 2026-08-30
GitHub 信息
- 许可证
- MIT
- 主要语言
- JavaScript
- 最近推送
- 2026年8月28日 10:21
- 维护者
- WSL043
- 收录日期
- 2026-08-30
README 演示图
从仓库 README 提取的截图/GIF（已过滤徽章、头像等装饰图）。
DSH Dictation in the official DeepSeek Harness composer
https://raw.githubusercontent.com/WSL043/dsh-dictation/main/docs/images/dictation-composer-dark-en.png
Dictation sources and local model management
https://raw.githubusercontent.com/WSL043/dsh-dictation/main/docs/images/dictation-settings-dark-en.png
安装
dsh plugin --profile web add dsh-dictation标签
README 徽章
将这段 Markdown 添加到插件 README，链接到对应的详情页。
[](https://dshget.com/plugins/WSL043/dsh-dictation)相关插件
开发与运行时dsh-talk
Voice-first session loop for DeepSeek Harness: a composer microphone button with browser/local speech-to-text (Web Speech, FunASR, whisper.cpp), a speak tool for text-to-speech replies (browser, edge-tts, piper), event announcements with mute, and speak-to-interrupt.
open-design
★ 92718Local-first design product: detects your installed code-agent CLI, runs design skills + design systems, streams artifacts into a sandboxed preview.
archify
★ 32709Agent skill for beautiful, verifiable architecture, workflow, sequence, data-flow, and lifecycle diagrams—self-contained HTML with motion and crisp export.