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 ke
Author: wangzhanchao883 · Voice & Audio · Catalog snapshot: 2026-09-16Hold-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 ke
Imported third-party catalog description; not a Registry verification conclusion.wangzhanchao883/dsh-hold-to-talk
— stars · 0 downloads
Signals were provided by the source catalog and do not imply quality or safety. 2026-09-16No exact-version test is available.
No Registry security conclusion is available.
No functional smoke evidence is available.
Plugin permissions have not been resolved.
Package structure and integrity have not been analyzed.
Describe your task in a DSH conversation and mention dsh-hold-to-talk. After installing or updating the manager from npm latest, it can find this candidate through Registry, then inspect its actual source and version locally.
dsh-hold-to-talkExact version not resolvedgithub:wangzhanchao883/dsh-hold-to-talkExact version not resolved