dsh-speak
Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices)
5 results
Make your AI harness speak — voice announcements for DSH and other AI coding harnesses (Windows SAPI5 + macOS system voices)
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.
A DSH todo plugin: extracts key items from conversations (natural chat, notifications, announcements, emails) into dated todos, with todo_* agent tools, a /api/todo REST API, and a sidebar To Do List entry. DSH 待办事项插件:从自然对话、通知、公告、邮件等对话内容中提取关键事项,转为带截止日期的待办,提供 todo_* 模型工具、/api/todo REST 接口与侧栏「待办事项」入口。
Official GitHub Discussions radar for DeepSeek Harness (dsh): list, filter and search the deepseek-ai/deepseek-harness discussion boards (Ideas / Q&A / Show Your Plugins / General / Announcements) from inside dsh. CLI + agent-callable discussions_radar tool, zero runtime dependencies, read-only.
MiniMax speech-to-text (asr-1.0) and text-to-speech (speech-2.8-hd) as a global DeepSeek Harness plugin: a transcribe_audio tool, an announce_speech tool, a settings card, composer voice input, spoken turn announcements, and handsfree conversation.