{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "title": "TranscriptionResponse",
  "type": "object",
  "properties": {
    "text": {
      "type": "string",
      "description": "The transcribed text."
    },
    "task": {
      "type": "string",
      "description": "The task performed, always transcribe."
    },
    "language": {
      "type": "string",
      "description": "The detected or specified language of the audio."
    },
    "duration": {
      "type": "number",
      "description": "The duration of the input audio in seconds."
    },
    "words": {
      "type": "array",
      "description": "Extracted words and their corresponding timestamps. Only present when timestamp_granularities includes word."
    },
    "segments": {
      "type": "array",
      "description": "Segments of the transcribed text and their corresponding details. Only present when timestamp_granularities includes segment or response_format is verbose_json."
    }
  }
}