- Cloudflare-hosted
Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multitasking model that can perform multilingual speech recognition, speech translation, and language identification.
| Model Info | |
|---|---|
| More information | link ↗ |
| Unit Pricing | $0.00045 per audio minute |
Parameters
Option 1
stringformat: binary
▶Option 2{}
object
text
stringThe transcriptionword_count
number▶words[]
arrayvtt
string