Wispr Flow Launches In-House Voice Model Canto 1

Wispr Flow has shifted from renting speech engines to its own model Canto 1, which tops dictation benchmarks with a 3.4% word error rate and 54% fewer edits, led by former Alexa founding scientist Ariya Rastrow.

2026-11-16 ~ 2026-11-16 · 2 related posts

• Wispr Flow's in-house Canto 1 speech model tops voicearena dictation benchmark — Scobleizer · 2026-11-16
• Wispr's self-trained Canto 1 speech model hits 3.4% WER on real-world dictation — rohanpaul_ai · 2026-11-16