dsh-hold-to-talk
Hold To Talk
Hold-to-talk voice input for the DeepSeek Harness Web composer: hold the mouse on the input box, speak, see the running transcript float above it, release to insert the text into the draft. Recognition runs locally (SenseVoice via sherpa-onnx) — no API key, offline, audio never leaves the machine. 微
The plugin will be installed here. Keep web if you are unsure.
npx -y @deepseek-ai/dsh plugin --profile web add github:wangzhanchao883/dsh-hold-to-talk#9b9521d1e527fd4d8c0b96d1c87bd9cc3926fe8b
Description
Hold-to-talk voice input for the DeepSeek Harness Web composer: hold the mouse on the input box, speak, see the running transcript float above it, release to insert the text into the draft. Recognition runs locally (SenseVoice via sherpa-onnx) — no API key, offline, audio never leaves the machine. 微信电脑版同款长按语音输入:在输入框上按住鼠标说话,浮层里边说边出字,松手把文字写进输入框,上滑取消;识别在本机跑,免密钥、离线、音频不出本机。
Compatibility and provenance
Hold To Talk is published as dsh-hold-to-talk and currently resolves to version 0.1.4. The Hub verifies its manifest and preserves the exact installation source for reproducible installs.
- DSH compatibility
- *
- Runtime surfaces
- web
- Release source
- github
- Registry updated