Speech recognition

Speech-to-text that does not need a data centre.

On-device STT means the weights sit on your own disk and inference runs on your own Mac or PC. VV’s English default is Parakeet. You can try other local models from Experimental settings; you do not have to.

This is slower to download the first time and faster every time after, because there is no upload. Offline aeroplane dictation works.

Deep dive: on-device feature. Competitor context: Wispr Flow.