gpt-4o-transcribe-diarize

by OpenAI

GPT-4o Transcribe Diarize is an automatic speech recognition (ASR) model with built-in speaker diarization, meaning it can associate audio segments in a conversation with different speakers.

API Pricing

Input$2.5 / 1M tokens
Output$10 / 1M tokens

Specifications

Context window16,000 tokens
Modalitiestext, audio
Featuresthinking, function_calling, structured_outputs

Use gpt-4o-transcribe-diarize via the AIHubMix unified API — one interface for every major LLM.