{
  "_readme": "Two-layer script example. Bare string = display and spoken identical; object = they diverge (display for captions, spoken for TTS). One line = one caption phrase (≤ ~40 display chars). vo-spoken.txt = all spoken forms joined.",
  "lines": [
    { "id": "l1", "tokens": ["This", "week", "at", "HyperFrames", "—"] },
    { "id": "l2", "tokens": ["fifteen", "releases,", "and", "one", "big", "story."] },
    { "id": "l3", "tokens": ["Feed", "it", "a", "Figma", "frame,"] },
    { "id": "l4", "tokens": ["get", "a", "working", "composition", "back", "—"] },
    { "id": "l5", "tokens": ["tokens,", "components,", "and", "motion", "all", "mapped."] },
    {
      "id": "l6",
      "tokens": [
        "Even",
        "the",
        { "display": "JSON", "spoken": "jay-sawn" },
        "manifest",
        "comes",
        "along."
      ]
    },
    {
      "id": "l7",
      "tokens": ["And", "it's", "all", "one", { "display": "CLI", "spoken": "C L I" }, "command."]
    },
    {
      "id": "l8",
      "tokens": [
        "See",
        "everything",
        "at",
        { "display": "hyperframes.heygen.com", "spoken": "hyperframes dot hey-jen dot com" }
      ]
    }
  ]
}