Privacy

The short version — your voice stays on your Mac.

Whisper Face is local-first by design, not as a setting you have to find.

What stays on your Mac

Everything about what you said. Listening, recognition, cleanup, and insertion all run on-device. There are no cloud calls in the dictation path, so you can turn off Wi-Fi and keep working.

What we never collect

• No audio is uploaded, ever.
• No transcript is stored on anyone else’s server.
• No telemetry follows your usage around.
• No behavioral profile is built from how or what you dictate.

Corrections stay yours

When you correct something, it becomes a small local rule you can read, edit, and delete. Personalization lives on your machine as inspectable rules and regression cases, not as a cloud dossier.

Support bundles

If you ask for help, Diagnostics can write a support bundle. It is saved with owner-only permissions to a location you choose, it is never uploaded on its own, and it contains only allowlisted health, permission, model, and aggregate result metadata — no transcripts.

For the full policy, see PRIVACY.md in the repository.