dsh-voice-assistant
Voice assistant for dsh web: say the wake phrase (e.g. "小鲸") to activate hands-free dictation — what you say is transcribed and typed into the chat box automatically. Supports spoken edit commands (send, clear, new line, stop reading) and reads assistant replies aloud in Chinese. Speech recognition runs locally in-browser via sherpa-onnx WASM, so it works offline without an API key.
dsh web 语音助手：说出唤醒词（如「小鲸」）即可免手听写，说话内容自动转成文字填入输入框；支持口述编辑指令（发送、清空、换行、停止朗读），并可用中文朗读 AI 回复。语音识别基于 sherpa-onnx WASM 在浏览器本地运行，离线可用、无需 API Key。
How to install
dsh plugin add dsh-voice-assistant About
🎙️ dsh-voice-assistant **dsh web 免手语音助手** —— 关键词唤醒 · 语音听写 · 口述编辑 · 中文朗读 在 dsh web 输入框旁提供麦克风按钮与科幻风状态条，让你**彻底解放双手**：说「小鲸」唤醒，口述指令自动入框，回复自动朗读——全程不离键盘，不碰鼠标。 **识别引擎默认使用 sherpa-onnx WASM 在浏览器本地运行**：模型跑在浏览器里，**离线可用、不依赖 Google 服务**，国内网络无需任何代理。仅在本地资源加载失败时自动回退浏览器 Web Speech API。 --- ✨ 功能特性 | 能力 | 说明 | | --- | --- | | 🎤 **关键词唤醒** | 说「小鲸」（或任意自定义词）唤醒。**同音/近音容错自动生效**：同音字直接唤醒；近音字需 3s 内二次确认（防误唤醒，可关） | | ⚡ **实时响应** | 利用流式中间结果**不等整句说完**：唤醒词一出口立即唤醒，口述命令（执行发送/执行清空等）边说边执行，无需等待静默判定 | | 🗣️ **语音听写** | 唤醒后连续口述，逐句自动填入输入框，30s 无语音自动回待命 | | ✏️ **口述编辑命令** | 所有命令以「执行」开头（如「执行删除上一句」「执行发送」），正文中的「发送/清空/删除」等词**永不误触**；含**同音字容错*…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 3
- mo. downloads
- 1.0K
- Last push
- 2026-09-02
- Created
- 2026-08-29
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- deepseek-harness, dsh-plugin, dsh-plugin-desktop, dsh-plugin-market
Related plugins
dsh-voice-scribe
PensiveFei/dsh-voice-scribe
Voice input for the web UI: tap Alt (or Alt+Space) to start/stop dictation, browser Web Speech (zero-config) or OpenAI-compatible cloud ASR, optional polish through DSH-configured LLM, settings UI.
dsh-tts
GooDAnDReaDY/dsh-tts
Speaks agent replies in the DeepSeek Harness web UI through a provider fallback chain (OpenAI, ElevenLabs, Google, Azure, Groq, Deepgram, OpenRouter, Edge, Piper, eSpeak), so a failing or rate-limited provider falls through to the next instead of going silent.
dsh-ears
WizisCool/dsh-ears
Voice input plugin for DeepSeek Harness (dsh): a microphone button in the composer turns speech into a draft transcript, with a choice of speech-recognition backends, optional polish through dsh own LLM routes, and a native settings page.
dsh-omi-voice
PolinniZhong/dsh-omi-voice
In-chat read-aloud for DeepSeek Harness: tap to read, pause and resume AI replies with natural Doubao TTS voices (BYOK), reading only the final answer with code, tables and diagrams filtered; local engine, plugin keeps no API key.