17.09.2026 • Research • 10 min

Canto: a speech model built for the real world

Wispr AI Lab,

Check out our latest articles

Wispr Flow ranks #1 on Voice Arena's independent Dictation Bench

Wispr Flow ranks #1 on Voice Arena's independent Dictation Bench, outperforming 10 Mac dictation apps with a 79.4% ready-to-send rate and minimal edits.

12.11.2026 • Research

Canto 1: A speech model that gets better with use

Two months after launch, Canto is making Wispr Flow faster and more accurate—with fewer edits, less waiting, and more words dictated.

09.11.2026 • Research

Advancing HCI

Wispr is rethinking human-computer interaction — reducing cognitive friction so technology finally feels effortless, intuitive, and built around how you think.

06.05.2026 • Insights

Help build the interface between humans and intelligence.