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.
面向 DeepSeek Harness (dsh) 的语音输入插件：输入框的麦克风按钮把语音转成草稿文本，支持多种语音识别后端，可选经 dsh 自有 LLM 路由润色，并带原生设置页。
How to install
dsh plugin add dsh-ears About
简体中文 · text 麦克风 → 转写 → 可选润色 → 可编辑草稿 → 手动发送 https://github.com/user-attachments/assets/1363768e-a393-44bd-a008-1ce2055cac41 --- 识别后端支持浏览器原生 Web Speech、本机 Whisper、Groq、阿里云百炼，以及任意 OpenAI 兼容转写接口。润色可以选择 dsh 里已经接好的任何模型，提示词可以自定义。默认快捷键 Ctrl+Shift+Space。 安装 前置依赖：DeepSeek Harness（0.1.0-rc.6、rc.7 或 rc.8），Node.js ^22.19.0 || >=24.0.0。 **从 npm 安装：** sh dsh plugin --profile web add dsh-ears 如果还没安装 dsh CLI： sh npx -y @deepseek-ai/dsh plugin --profile web add dsh-ears **从源码安装：** sh git clone https://github.com/WizisCool/dsh-ears.git cd dsh-ears pnpm install pnpm build dsh plugin --profile web add "$PWD" 安装完成后…
Recommendation signals
Meta
- License
- MIT
- Language
- TypeScript
- GitHub stars
- 7
- mo. downloads
- 187
- Last push
- 2026-08-20
- Created
- 2026-08-15
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- asr, deepseek-harness, dsh, dsh-plugin, speech-to-text, voice, whisper
Related plugins
dsh-voice
STARDUSTLC666/dsh-voice
Voice pair: free edge-tts neural speech synthesis + OpenAI-compatible ASR transcription.
dsh-voice
haoku123/dsh-voice
Full-duplex voice mode for the Web UI: tap-to-toggle or hold-to-talk dictation (send key or `Ctrl`) with a live caption, host-side SenseVoice ASR via sherpa-onnx, sentence-by-sentence spoken replies, and speaking interrupts playback and the running turn (true barge-in). No API key.
dsh-dingo
february2015/dsh-dingo
Sound reminders with one-click jump for concurrent sessions: the current session gets crisp dang/dang-dang tones, other sessions a soft ding/ding-ding plus a top-right card that jumps straight to the replying conversation.
dsh-voice-call
PandaPolo/dsh-voice-call
Agent-initiated voice calls: `offer_call` rings the human (接听/拒接/稍后再说); accepted calls synthesize and play locally via CrispASR + Qwen3-TTS (9 speakers, 2 Chinese dialects), rejected calls return the decision to the agent.