Catalog · 40 models · 13 providers
Every speech-to-text model worth using, one rate card.
40
Total models
106
Languages
$0.0022
Cheapest /min
22.8%
Best WER
2 models
filtered from 40
Cartesia
Cartesia's newest streaming STT — lowest WER of any streaming model, native turn detection, and robust on alphanumerics like phone numbers, emails, and UUIDs. English only for now.
Realtime model — batch benchmarks not applicable
Speed Factor
0.1x
Billing
per 1s
Retention
1 languages
(view all)
Cartesia
Whisper rearchitected for real-time and batch voice AI — fastest TTCT, 99-language coverage
WER
CER
Speed Factor
0.1x
Uptime
Billing
per 1s
Retention
100 languages
(view all)