Overview
dsh-speech-plugin
Speech plugin for DeepSeek Harness: per-message speak button, composer voice input, and auto-announce toggle, over cloud TTS/ASR with Web Speech API fallback
README / EN
Package documentation
Registry summary
Speech plugin for DeepSeek Harness: per-message speak button, composer voice input, and auto-announce toggle, over cloud TTS/ASR with Web Speech API fallback
dsh.pub verifies the pinned bundle contract, runtime facts, and distribution semantics. The complete README remains in the source repository.
Read the full README on GitHubLIMITATIONS
Known limitations
- 引擎与音色是部署级配置，浏览器内切换音色的 UI 未做。 - 自动播报按「新完成」触发；切换会话期间，旧会话仍在生成的消息完成时也会播报。 - 语音输入是开放麦克风，不做说话人分离：录音期间环境人声也会被识别。 - 回退的系统音色质量取决于操作系统；macOS 可在 系统设置 → 辅助功能 → 朗读内容 下载增强版中文音色。