OpenAI: gpt-4o-transcribe-diarize API
An advanced ASR model powered by GPT-4o that automatically identifies different speakers and timestamps. Optimized for multi-speaker environments like meetings and interviews, it provides speaker-labeled JSON transcripts with higher accuracy than Whisper in complex acoustic scenarios.
- Context window: 16,000 tokens
- Input: audio
- Output: text
- Released: 2025-10-17
- Knowledge cutoff: 2024-05-31
Frequently Asked Questions
What is the context window of gpt-4o-transcribe-diarize?
gpt-4o-transcribe-diarize supports a context window of up to 16,000 tokens.
What is the knowledge cutoff of gpt-4o-transcribe-diarize?
The knowledge cutoff of gpt-4o-transcribe-diarize is 2024-05-31.