GPT-4o Transcribe Diarize
JSON →A specialized variant of OpenAI's GPT-4o model for transcribing audio with speaker diarization to distinguish multiple speakers.
Specs
context window 16K tokens
max output 2K tokens
input price $2.5 / 1M tokens
output price $10 / 1M tokens
Capabilities
streaming
Dates
releasedSep 2025
knowledge cutoffJun 2025
Resources
API
full doc /v1/models/gpt-4o-transcribe-diarize