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.
面向 Web UI 的语音输入插件：点按 Alt（或 Alt+空格）开始/停止听写，支持浏览器内置 Web Speech（零配置）或 OpenAI 兼容云端 ASR，可选经 DSH 已配置模型润色，带设置页。
How to install
dsh plugin add dsh-voice-scribe About
dsh-voice-scribe DSH 专属语音输入插件：**点按 Alt 说话、再点按转文字**，插入输入框光标处。 Voice input for DeepSeek Harness: tap Alt to talk, tap again to get text. ⚠️ 非官方插件，与 DeepSeek / 深度求索公司无关联。使用前请阅读 SECURITY.md。 安装 Install bash dsh plugin --profile web add dsh-voice-scribe # 重启 dsh web 后生效 使用 Usage 点输入框 → 按 **Alt** 开始说话 → 再按 **Alt** 结束并转写（备选热键 **Alt+空格**，设置可切换）。 识别引擎 Engine（默认「自动」，零配置） | 引擎 | 说明 | |---|---| | **自动（默认）** | 本地离线识别优先；不可用时自动回退浏览器识别 | | 本地离线识别 | SenseVoice，零配置零 key、**音频不出本机**；首次使用自动下载模型（约 230MB，国内镜像，只需一次） | | 浏览器 Web Speech | 零配置；依赖 Google/Microsoft 服务（国内 / Edge Stable 可能不可用） | | 云端 ASR（可选） | OpenAI 兼容端点，需…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 33
- mo. downloads
- 3.4K
- Last push
- 2026-09-24
- Created
- 2026-08-25
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- asr, deepseek-harness, dsh-plugin, speech-to-text, voice-input, voice-recognition
Related plugins
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.
dsh-voice-call
biliye/dsh-voice-call
Voice call assistant for the DSH Web GUI: a draggable floating call ball, browser-side VAD that sends each utterance after a pause, FunASR HTTP or streaming speech recognition, MiniMax or OpenAI-compatible TTS replies, an optional wake-word mode with auto-sleep, and task dispatch to separate subagent sessions with progress, stop, and spoken completion reports.