Pular para o conteúdo
OpenAI logo

whisper

Automatic Speech Recognition • OpenAI

Ver como Markdown
  • 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
text
stringThe transcription
word_count
number
vtt
string

API Schemas (Raw)

Input
Output