Skip to main content
Superwhisper recording window showing live realtime transcription while dictating

​
Overview

Realtime transcription shows your words on screen as you speak, so you get immediate feedback on accuracy. It works only with voice models that support streaming:
  • Nova (Cloud): requires an internet connection
  • Parakeet Realtime (Local): runs on your device and works offline
If the Realtime toggle is missing or grayed out, your mode uses a voice model that doesn’t support streaming. Switch to one of the models above.

​
Enable realtime transcription

1

Open the mode

Open Superwhisper and go to the mode you want to edit
2

Select a realtime-capable voice model

In the mode editor, set Voice Model to a Nova model (cloud) or a Parakeet realtime-capable model (local)
3

Enable Realtime

With a realtime-capable model selected, the Realtime toggle becomes available. Turn it onSuperwhisper mode editor with a Parakeet model selected and Realtime enabled