Awesome new release from the @WisprFlow team! Canto has the lowest word error rate of any speech model.
Introducing Canto, our latest speech model for real-time dictation.
On our evaluation of 9.8 hours of English Flow dictations from more than 2,300 speakers, Canto achieved a 3.4% word error rate—the lowest among the models we tested.
Learn more about Canto from our CSO, Ariya
00:00
