{
  "hq": [
    {
      "speaker": 0,
      "text": "Can say hi, Yuzu.",
      "start": 0.0,
      "end": 1.3
    },
    {
      "speaker": 1,
      "text": "Hi, Yuzu.",
      "start": 1.4399999,
      "end": 2.1799998
    },
    {
      "speaker": 0,
      "text": "So now it's recording that video.",
      "start": 2.48,
      "end": 4.4
    },
    {
      "speaker": 1,
      "text": "Okay. And yeah. It's recording a video when you're looking. Like, every piece. Once",
      "start": 4.4,
      "end": 11.679999
    },
    {
      "speaker": 0,
      "text": "you double tap it. And if you",
      "start": 11.679999,
      "end": 13.185
    }
  ]
}