Whisper Large V3 is OpenAI's open-weight speech recognition model with about 1.55B parameters, trained on more than 5 million hours of audio. It transcribes speech in 99 languages and can translate speech into English, and compared with Large V2 it uses 128 Mel frequency bins and adds Cantonese.
Modalities
In / out price
$0.006/min
Context
–
Max output
–
Updated
Oct 22, 2026
Providers
0 routesCompare providers by price, privacy, and speed.
No provider route for this model is live right now.
Privacy
0 / 4No live route
AnonRouter is not currently offering a callable provider route for this model.
Features
No feature flags reported for this route.
Uptime
FAQ
Common questions about Whisper Large V3.