Skip to main content
POST
Speech to text
Transcribe an audio file into text.

Request

Parameters

Response

response_format: "json":
response_format: "verbose_json":
srt / vtt return subtitle text (save directly as .srt / .vtt).

Python

Long-audio strategy

  • Whisper has a 25MB single-file limit; split long audio in advance (5-10 minutes per segment recommended).
  • Use prompt to pass the tail text of the previous segment to keep context coherent.
  • A tool like ffmpeg -i input.mp3 -f segment -segment_time 600 part_%03d.mp3 can split quickly.

Billing

Charged by audio duration (seconds); the specific multipliers are subject to the console.