dsh-voice-input

What it doesAI

System-wide voice input that transcribes speech to text at cursor using local Whisper model.

• Hold F2 to dictate, text pasted at cursor
• Fully local, no internet or API fees
• Good Chinese support, Nvidia GPU acceleration

AI-generated from the repo README — for reference only.

Installation

Install method: GitHub · not yet tested in container (L3+)

Compatibility

Requirements

• • Node.js: not stated
• • DSH: declared "not stated"
• • External credentials: none detected

Security Report

Automated static scan, not manual review.

DSH.SO VETPASSEDb59559

Security reviewAutomated review · daily

PASSED

Vet static analysis found no suspicious behavior — verdict is clean.

0 critical·0 high·0 medium·100 score

Version binding

plugin version0.2.0dsh manifest

scanned commitb59559113e592026-08-21

latest commitb59559113e59

vet verdictclean · gitscore 100

Vet is an AST static scan (npm artifact or git source).

`[![dsh.so security](https://www.dsh.so/badge/dsh-voice-input-9.svg)](https://www.dsh.so/artifact/dsh-voice-input-9/)`

Disclaimer: automated static analysis, not a security guarantee. Always review what you install.

Activity

Last commit 2026-08-15 · activity: Active

Source

GitHub: github.com/lougyang/dsh-voice-input