{
  "automatic": {
    "width": 1080,
    "height": 1920,
    "fps": 30,
    "durationSeconds": {"min": 25, "max": 35},
    "audioStreams": 1,
    "maxSilenceGapSeconds": 0.25
  },
  "human": [
    "Each A-versus-B pair answers one clear viewer question, and its labels name the contrast.",
    "All fifteen sentences sound complete and natural when read aloud.",
    "Each spoken line has a matching visual proof.",
    "Each proof image is a tight crop that communicates one point at phone size in under one second.",
    "The same bundled character pose pack is reused throughout.",
    "The character never lip-syncs or acts as the narrator.",
    "Proof images stay at the top on a plain white canvas.",
    "Handwritten captions are short and readable.",
    "The voice resembles the authorized source and pronounces every word correctly."
  ]
}