dsh-plugin-voz-copilot：为 DeepSeek Harness 提供语音副驾驶
dsh-plugin-voz-copilot 由 songjongdevsecops 维护，为 DeepSeek Harness 提供 Voice copilot：命名并绑定 push-to-talk 会话、扩展 Composer 麦克风，并运行含 Silero VAD、推测式转写、流式 TTS 与说话人校验的实时语音对话环。文章说明插件定位、核心能力与 DSH 插件生态背景；因公开 README 未抓取且无法核实官方安装命令，安装须以 SkillHub 目录页与 GitHub 文档为准，并提醒在 dsh 进程权限下审阅源码与许可证。
Read Moredsh-voice-chat: A Voice Chat Plugin for DeepSeek Harness
The DeepSeek Harness plugin `dsh-voice-chat` delivers a closed-loop voice interaction in the Web GUI. When users click the microphone to speak, the system automatically converts the voice to text and sends it to the AI after a 2.5-second pause, and the AI's response is then automatically read aloud via TTS. The plugin supports multiple ASR and TTS engines with independent configurations. Core features include single-channel playback, interrupting previous audio, preventing re-playback, and mute control. Installation requires Node.js ≥ 22 and running `dsh web`. It supports keyboard shortcuts and configuration file overrides, making it ideal for developers seeking natural voice interactions.
Read MoreDeepSeek Harness Voice Conversation Plugin: dsh-voco
`dsh-voco` is a voice conversation plugin for the DeepSeek Harness (DSH) Web UI, designed to manage background Agent tasks through natural language and improve operational efficiency. The plugin uses SiliconFlow's ASR model and Edge TTS to perform speech recognition and synthesis, supports delegating voice commands to background Agents for processing, and provides immediate voice feedback and session persistence. Installation requires Node.js 22.19+ and a configured SiliconFlow API key, which can be set through the DSH Web UI or environment variables.
Read MoreDeepSeek Harness Voice Dialog Plugin Introduction
The DeepSeek Harness plugin `lak321/dsh-voice-chat` provides fully client-side voice interaction without requiring server-side support. Its core features include using the Web Speech API for speech input and text-to-speech (TTS) output, with support for multiple languages and adjustable speech rate and pitch; automatically removing Markdown markers to prevent unwanted noise; and saving settings via localStorage. It can be installed with `dsh plugin --profile web add "github:lak321/dsh-voice-chat#<commit>&path:/"`. Development requires adherence to React Hook rules and the `exports.inject` export requirement.
Read More