jsoncode/dsh-voice-input-qwen-asr ↗★ 0
dsh-voice-input-qwen-asr
Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run server). Bilingual UI (zh/en)
安装
$
npx -p @deepseek-ai/dsh dsh plugin --profile web add github:jsoncode/dsh-voice-input-qwen-asr说明文档
阅读完整 README ↗Usage
- Open Settings → Voice, press Install all (or run the four steps individually): clone runtime → clone model → create virtualenv → install deps. Watch the install log; the deps step downloads torch and may take a while.
pipmirror can be configured on the same page. - Press Start service and wait until the state chip turns "Running" (device shows
cuda:0orcpu). - In any chat, click the mic button left of the send button, speak, then press Done, insert — the recognized text is appended to the input draft. "Cancel" discards the recording.