Whisper

openai/whisper-1

A speech-to-text model, at $0.0063 per minute.

Details

Maker: openai
Kind: Transcription
Price: $0.0063 per minute
Capabilities: None listed
Takes: Audio
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2022-09-21
Retiring: Scheduled for removal on 2027-02-26
phantom-1: phantom-1 runs transcription on this model. How phantom-1 picks

Description

Whisper is a general-purpose speech recognition model, trained on a large dataset of diverse audio. You can also use it as a multitask model to perform multilingual speech recognition as well as speech translation and language identification.

Call it

curl

curl https://phantom.codes/v1/audio/transcriptions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -F file=@audio.mp3 \
  -F model=openai/whisper-1

Set PHANTOM_KEY to your key. Any OpenAI client works with the base URL https://phantom.codes/v1.

Get a key Compare with another model