Offline
The model lives on your laptop.
Recognition runs on your own computer, an Apple silicon Mac or a Windows PC. Your audio has no network path to travel.
The default English model downloads once, about a gigabyte, and is then used for every dictation. Other languages are optional downloads from inside the app.
Because nothing is streamed, latency is set by your processor rather than a round-trip to a data center. Modern laptops keep up as you speak.
Optional features that call a cloud language model are clearly labeled and off by default: a transform you point at a cloud provider yourself, and, in Pro, Cloud Polish. Both send text only, never audio. Read the privacy policy for the exact list.
Related: Why offline matters Privacy policy Transforms