WisprFlow launches Canto speech model with 3.4% word error rate for real-time dictation

Scobleizer · x · 2026-09-18

Voice-input tool WisprFlow has released Canto, its latest real-time dictation speech model. On an 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 the company tested.

Original post →

More from Models

Models channel →