Transcribe audio

Produce a transcript from an audio or video file using the model configured on this machine.

Check for a config first

Settings live in ~/.config/transcribe-audio/config.json.

• Missing — the machine isn't set up. Read references/setup.md and run setup (staging area, then model choice) before transcribing. Don't pick a model unprompted: the right one depends on the user's hardware, languages, and whether they want speed or accuracy, and a wrong guess wastes a large download.
• Present — go straight to transcribing.

When the user asks to change or upgrade their model, route to references/setup.md as well.

Transcribe

Run the bundled script on the file: