Models / openai / GPT-4o Transcribe

GPT-4o Transcribe

openaiaudio

A speech-to-text model in the GPT-4o family designed for high-accuracy audio transcription.

audiotextstreaming

homepage ↗docs ↗

Specs

Context & limits

16K

context window

2K

max output

Lifecycle

Dates

released2025-03-01

Resources

homepagehttps://platform.openai.com/docs/models/gpt-4o-transcribe ↗

docshttps://platform.openai.com/docs/api-reference/audio ↗