dsh-voice-input-cn
China-ready voice input for the composer. Requires a local Python bridge (pip install dashscope websockets, run bridge/voice-bridge.py) — the plugin alone does not work. Browser mic streams 16 kHz PCM to the bridge, which runs Alibaba Cloud DashScope ASR (paraformer-realtime-v2); interim text fills the draft at the cursor, silence auto-stop, optional auto-send.
国内可用的输入框语音输入。需要先启动本地 Python bridge（pip install dashscope websockets，运行 bridge/voice-bridge.py）——只装插件不可用。浏览器麦克风采集 16kHz PCM 流式转发给 bridge，由阿里云 DashScope ASR（paraformer-realtime-v2）识别；识别文字在光标处实时填入草稿，静音自动停止，可选识别后自动发送。
How to install
dsh plugin add dsh-voice-input-cn About
dsh-voice-input-cn **DeepSeek Harness Web 语音输入插件（国内可用版）** 在聊天输入框添加麦克风按钮，点击说话即可将语音转为文字填入草稿。基于 **阿里云 DashScope ASR**（国内直连可用），替代原版依赖的 Google Web Speech API（国内无法访问）。 **本项目 fork 自 NewDaNew/dsh-voice-input**，原版使用 Web Speech API（Google 云端），在国内直连不可用；本版重写了识别引擎为**阿里云 DashScope ASR + 本地 bridge**。 **🛠 开发工具**：本插件在 **DeepSeek Harness (DSH)** 中开发与调试（代码重构、排障、测试均由 DSH 辅助完成）。DSH 是一个开源 AI 助手框架：https://github.com/deepseek-ai/dsh --- ✨ 功能 🎤 输入框麦克风按钮，点击开始说话，静音 1.5 秒自动停止 📝 识别文字**实时填入输入框**（光标位置插入，不覆盖已有草稿） 🔀 中文 / English 语言切换 📨 可选"识别后自动发送" 🔌 本地 bridge（Python）中转，国内直连阿里云，低延迟 🧱 架构 浏览器插件 (lib/client.js) ├─ AudioWor…
Recommendation signals
Meta
- License
- MIT
- Language
- JavaScript
- GitHub stars
- 0
- mo. downloads
- –
- Last push
- 2026-08-20
- Created
- 2026-08-19
Links
Basic safety check
- Findings
- None
- Sources
- curated:awesome-dsh-plugin.com, curated:awesome-dsh-plugin/awesome-dsh-plugin
- Topics
- dsh-plugin
Related plugins
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-voice-webspeech
anweat/dsh-voice-webspeech
Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).
dsh-fish-tts
MaRi23333/dsh-fish-tts
Reads assistant replies aloud via Fish Audio API only (bring your own key): per-message read-aloud, auto-read toggle, and a settings page for model, voice reference_id, encrypted API key, and proxy.
dsh-voice-input-plugin
Zhangbo-cn/dsh-voice-input-plugin
Composer mic for the Web UI: tap-to-monitor live transcription and hold-to-talk, with host Edge TTS reply reading that streams while the model generates, echo-pause during reading, and tap-to-stop.