Whisper running on your Mac. Plain-Markdown notes in a folder you pick. Nothing uploaded to OpenAI, Otter, or anyone else. The same words your consent form already says.
Whisper large-v3 transcribes locally. The audio file is deleted unless you keep it. One outbound network call per day — a license check. Air-gap after activation if you need to.
Front-matter has participant ID, date, duration. Body is clean Whisper output. Easy to anonymise, easy to import, easy to cite.
Drag a folder of .m4a or .wav onto the tray. Each file becomes a Markdown note. No CLI, no Python env, no GPU drivers.
Auto-detect or set per-note. Code-switching interviews (KR + EN) stay coherent — large-v3 handles them well. Tested daily on Korean academic interviews.
Mic-only mode for in-person. ⌘R from the menu bar starts a recording — no laptop full-screen, no awkward bot in the room.
One-time license. Cheaper than three hours of Rev. Approve once, use it for the whole dissertation.
“Audio recordings will be transcribed using OpenAI Whisper running locally on the researcher’s device (Quietly, meetquietly.com). No audio or transcript will be transmitted to a third-party server. Recordings will be deleted after transcription; anonymised transcripts will be retained for analysis.”
We’re happy to provide a one-page technical brief for your IRB. Email support@meetquietly.com.
7-day trial, no card. 30-day refund. macOS 13+.