GPT-4o Transcribe

openai/gpt-4o-transcribe

A speech-to-text model, at $3.15 per million tokens.

Details

Maker: openai
Kind: Transcription
Context window: 0 tokens
Input: $3.15 per million tokens
Capabilities: None listed
Takes: Audio
Returns: Text
Zero data retention: Not on every provider
No training on requests: Yes, on every provider
Released: 2024-03-13
Retiring: Scheduled for removal on 2027-02-26

Description

GPT-4o Transcribe is a speech-to-text model that uses GPT-4o to transcribe audio. It offers improvements to word error rate and better language recognition and accuracy compared to original Whisper models. Use it for more accurate transcripts.

Call it

curl

curl https://phantom.codes/v1/audio/transcriptions \
  -H "Authorization: Bearer $PHANTOM_KEY" \
  -F file=@audio.mp3 \
  -F model=openai/gpt-4o-transcribe

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