Fact · Voice and AI
Superwhisper's models page says its on-device transcription runs on the device, and that audio never leaves the device.
Checked against its source on October 17, 2026
In the source's own words
“Audio never leaves the device and no internet connection is needed.”
AI Models in Superwhisper: Speech Recognition and Language Models, Superwhisper, 2026, On-device transcription.
Open the original- What it measures
- The page applies this to the local speech models, which run on the Mac, PC or iPhone. The cloud models are listed separately.
- What it does not show
- This describes the speech step only. If you turn on a cloud language model for the rewrite, the text sent to it leaves the device.