CommandVoice
Speak a thought. Keep your workflow.
My roleCreator
01 / The context
A problem worth exploring.
Typing can interrupt the flow of a thought. A desktop dictation tool can turn speech into text where the user is already working.
A Python desktop core for hotkey-triggered recording, faster-whisper transcription, clipboard delivery, and optional pasting into the active window.
02 / Inside the project
See how it works.
Choose a step, inspect the details, and explore the thinking behind the experience.
Illustrated Python core · fixed transcript · no microphone, hotkey, or clipboard access
A shortcut starts the desktop recorder.
Default stop shortcut: Ctrl + Shift + R. This webpage does not register either shortcut.
03 / Decisions & evidence
Behind the experience.
Approach & boundaries
The public source registers start and stop hotkeys, records audio, runs faster-whisper locally, and copies the transcript before optionally synthesizing a paste. Automatic model selection chooses base or large-v3 according to hardware. Model files may be downloaded; the inspected transcription path does not call a hosted speech API.
What the evidence shows
The public repository exposes a console-driven Python core. Its README mentions an independent Electron UI, but the UI and installers are not included. The illustration represents the verified core workflow, not a screenshot of that UI.
Sources & attribution
Reviewed against the linked public sources and supplied assets. Demonstrations on this page use fixed example content unless labeled as an original recording or screenshot.