Skip to main content

openai/gpt-4o-transcribe-diarize/speech-to-text

OpenAI’s GPT-4o Transcribe Diarize transcribes a recording from an audio URL and tags each segment with a speaker label and start and end times, for files up to 25 MB and two hours long, with an optional language hint.

From $0.0001/s

Workbench

These examples were written for this endpoint. Replace the prompt and sample media URLs with your own accessible inputs, then check the current quote and model availability before submitting.

  • Model reply

    { "durationSeconds": 2.35, "segments": [ { "end": 0.8500000000000003, "speakerId": "A", "start": 0, "text": " The next step is ready,", "type": "segment" }, { "end": 1.9500000000000004, "speakerId": "A", "start": 1.2000000000000004, "text": " please continue.", "type": "segment" } ], "text": "The next step is ready, please continue." }

    Transcribe a voice message
    • en
  • Model reply

    { "durationSeconds": 4.275, "segments": [ { "end": 1.55, "speakerId": "A", "start": 0, "text": " The API request uses JSON.", "type": "segment" }, { "end": 3.8999999999999995, "speakerId": "A", "start": 1.8499999999999999, "text": " Retry the webhook once after five seconds.", "type": "segment" } ], "text": "The API request uses JSON. Retry the webhook once after five seconds." }

    Recognize API terminology
    • en
  • Model reply

    { "durationSeconds": 6.2125, "segments": [ { "end": 1.95, "speakerId": "A", "start": 0, "text": " Can we publish the release on Friday morning?", "type": "segment" }, { "end": 2.8999999999999995, "speakerId": "B", "start": 2.6499999999999995, "text": " Yes,", "type": "segment" }, { "end": 4.3, "speakerId": "B", "start": 3.05, "text": " the final review is complete,", "type": "segment" }, { "end": 5.5, "speakerId": "B", "start": 4.6, "text": " and the release is ready.", "type": "segment" } ], "text": "Can we publish the release on Friday morning? Yes, the final review is complete, and the release is ready." }

    Two-speaker meeting
    • en

This example starts at $0.0001 per second of input audio. The Playground updates the estimate when you change the settings.