{
  "text": "Complex transcription with metadata.",
  "language": "en",
  "duration": 5.2,
  "segments": [
    {
      "text": "Complex transcription",
      "start": 0.0,
      "end": 2.1
    },
    {
      "text": "with metadata.",
      "start": 2.1,
      "end": 5.2
    }
  ],
  "usage": {
    "prompt_tokens": 3,
    "completion_tokens": 7,
    "total_tokens": 10
  }
}