GPT-4o Transcribe Diarize

JSON →
openai audio
audiotext

A specialized variant of OpenAI's GPT-4o model for transcribing audio with speaker diarization to distinguish multiple speakers.

context window 16K tokens
max output 2K tokens
input price $2.5 / 1M tokens
output price $10 / 1M tokens
streaming
releasedSep 2025
knowledge cutoffJun 2025