OpenAIGPT transcription

GPT-4o Transcribe Diarize

GPT-4o Transcribe Diarize adds speaker labels to speech transcription. OpenAI marks the release deprecated and documents access only through the Transcription API.

Deprecated API; check access details

Speaker segmentation is part of the result

Diarization associates time segments with different speakers. It does not by itself prove a speaker's real-world identity. The model produces text from audio and has a documented 2,000-token output limit.GPT-4o Transcribe Diarize official model documentation

Review an existing integration

Practical guidance. For meeting notes, review speaker changes, overlapping speech and attribution of decisions. A correct transcript can still assign a statement to the wrong participant. Let a reviewer correct speaker labels before using the result as a meeting record.

Specifications & access

GPT-4o Transcribe Diarize specifications
DetailValue and conditions
StatusDeprecated API; check access details
AccessAPI
Model identifiersgpt-4o-transcribe-diarize
Context window16,000 tokens

Published context for this deprecated release

GPT-4o Transcribe Diarize official model documentation
Maximum output2,000 tokens

Published maximum output, bounded by the remaining context

GPT-4o Transcribe Diarize official model documentation
Provider statusDeprecated in the current OpenAI model catalog; confirm remaining account access.GPT-4o Transcribe Diarize official model documentation

Related models

  • GPT-4o Transcribe

    OpenAI · GPT transcription

    GPT-4o Transcribe is a deprecated speech-recognition model based on GPT-4o.

    Launch date not confirmedDeprecated API; check access detailsAPI
  • GPT-Transcribe

    OpenAI · GPT transcription

    GPT-Transcribe turns recorded speech into text.

    Launch date not confirmedAPI
  • GPT-Live-Transcribe

    OpenAI · GPT transcription

    GPT-Live-Transcribe produces incremental text from live audio.

    Launch date not confirmedAPI
  • GPT-Realtime-Whisper

    OpenAI · GPT transcription

    GPT-Realtime-Whisper is a streaming transcription model for live speech.

    Launch date not confirmedAPI