heygen-com--hyperframes/skills/hyperframes-creative/frame-presets/creative-mode/caption-skin.html

<!--
  Creative Mode — caption skin (preset-local source).

  This is the preset's own lower-third karaoke caption look. product-launch-video's
  Step 2 copies it into the project as caption-skin.html; captions.mjs then fills the
  three reserved holes, wraps the fragment in a <template>, and writes
  compositions/captions.html:
    · the empty GROUPS array            → the engine's scene-aware word groups
    · the 0 duration + 0 width/height   → real total + canvas size
    · the empty data-brand-tokens style → :root tokens derived from the project's frame.md

  Token contract — reference ONLY this fixed vocab (captions.mjs injects it from
  frame.md, so the Step-2 brand overlay flows through; each var has a creative-mode
  literal fallback for standalone preview):
    --cap-ink · --cap-canvas · --cap-accent · --cap-accent-2 · --font-display ·
    --font-body · --cap-band-top · --cap-band-height
  Hooks (do not rename): .caption-group / .caption-word + states .is-active / .is-spoken,
  root data-composition-id="captions", timeline at window.__timelines["captions"].
  State changes use gsap.set({className}) (applied on the engine's frame-by-frame seek);
  never tl.call() callbacks (seek does not fire them → wrong state on render).

  Visual: a warm-cream card on a thick 4px ink border with a HARD offset shadow (a solid
  same-direction ink+orange duplicate, no blur — creative-mode's only depth device),
  square corners. Archivo Black, UPPERCASE, 0.92 line-height, ink glyphs. Upcoming words
  sit in faint ink; the current word becomes a solid yellow inked block (the brand's
  signature hard-offset-shadow accent block, no blur) with ink reading on top; spoken
  words settle to solid ink, the accent block cleared.
-->
<script src="https://cdn.jsdelivr.net/npm/gsap@3.14.2/dist/gsap.min.js"></script>

<!-- captions.mjs injects the project's :root tokens here -->
<style data-brand-tokens></style>

<style>
  #captions-root {
    position: absolute;
    inset: 0;
    pointer-events: none;
  }
  .caption-layer {
    position: absolute;
    inset: 0;
    z-index: 20;
    pointer-events: none;
  }
  /* the keep-out band, from captionBand(H) — frame content stays above it */
  .caption-stage {
    position: absolute;
    left: 0;
    right: 0;
    top: var(--cap-band-top, 900px);
    height: var(--cap-band-height, 180px);
    display: flex;
    align-items: center;
    justify-content: center;
  }
  .caption-group {
    /* every group is absolutely stacked over the SAME band — exactly one shown at a
       time via opacity. Must be absolute: in-flow groups would lay out side-by-side. */
    position: absolute;
    inset: 0;
    display: flex;
    align-items: center;
    justify-content: center;
    opacity: 0;
  }

  /* THE cream card — thick 4px ink border + the signature HARD offset shadow
     (a solid same-direction orange+ink duplicate, no blur), square corners */
  .caption-pill {
    max-width: 80%;
    padding: 18px 40px 22px;
    background: var(--cap-canvas, #efe9d9);
    border: 4px solid var(--cap-ink, #0f0f0f);
    border-radius: 0;
    box-shadow:
      14px 14px 0 var(--cap-accent-2, #e85a1f),
      14px 14px 0 4px var(--cap-ink, #0f0f0f);
  }
  .caption-line {
    display: flex;
    flex-wrap: wrap;
    justify-content: center;
    gap: 0.16em 0.3em;
    font-family: var(--font-display, "Archivo Black"), sans-serif;
    font-weight: 400;
    text-transform: uppercase;
    font-size: clamp(34px, 3.8vw, 52px);
    line-height: 0.92;
    letter-spacing: -0.01em;
  }

  /* upcoming — faint ink, no accent block */
  .caption-word {
    display: inline-block;
    padding: 0.02em 0.1em;
    color: color-mix(in srgb, var(--cap-ink, #0f0f0f) 38%, var(--cap-canvas, #efe9d9));
  }
  /* current word — THE hard yellow inked block (box-shadow spread = a hard square
     block w/o layout shift; no blur), ink reading on top */
  .caption-word.is-active {
    color: var(--cap-ink, #0f0f0f);
    background: var(--cap-accent, #f5c518);
    box-shadow: 0 0 0 0.08em var(--cap-accent, #f5c518);
  }
  /* already spoken — solid ink, accent block cleared */
  .caption-word.is-spoken {
    color: var(--cap-ink, #0f0f0f);
    background: transparent;
    box-shadow: none;
  }

  /* optional per-word accents (dormant until a word-classer tags them) */
  /* brand / key term — an inverted ink chip (the kicker-block voice) */
  .caption-word.cap-brand {
    color: var(--cap-canvas, #efe9d9);
    background: var(--cap-ink, #0f0f0f);
    box-shadow: 0 0 0 0.08em var(--cap-ink, #0f0f0f);
  }
  /* numerals / data — the mono voice, slightly recessed */
  .caption-word.cap-num {
    font-family: var(--font-body, "Space Grotesk"), ui-monospace, monospace;
    color: color-mix(in srgb, var(--cap-ink, #0f0f0f) 72%, var(--cap-canvas, #efe9d9));
  }
  /* emphasis — a thick orange underline (the counter accent) */
  .caption-word.cap-cta {
    text-decoration: underline;
    text-decoration-thickness: 3px;
    text-decoration-color: var(--cap-accent-2, #e85a1f);
    text-underline-offset: 0.12em;
  }

  @media (max-aspect-ratio: 9/16) {
    .caption-pill {
      max-width: 92%;
    }
    .caption-line {
      font-size: clamp(30px, 5vw, 44px);
    }
  }
</style>

<div
  id="captions-root"
  data-composition-id="captions"
  data-timeline-locked
  data-start="0"
  data-duration="0"
  data-fps="30"
  data-width="0"
  data-height="0"
>
  <div class="caption-layer" aria-hidden="true">
    <div id="caption-stage" class="caption-stage"></div>
  </div>
</div>

<script>
  // captions.mjs injects the engine's scene-aware groups + real duration here.
  var GROUPS = [];
  var DURATION = 0;

  (function () {
    var stage = document.getElementById("caption-stage");

    // build DOM: one .caption-group per group, .caption-word per word
    GROUPS.forEach(function (group, g) {
      var groupEl = document.createElement("div");
      groupEl.className = "caption-group";
      groupEl.id = "caption-group-" + g;
      var pill = document.createElement("div");
      pill.className = "caption-pill";
      var line = document.createElement("div");
      line.className = "caption-line";
      (group.words || []).forEach(function (w, i) {
        var span = document.createElement("span");
        span.className = "caption-word";
        span.id = "caption-word-" + g + "-" + i;
        span.textContent = String(w.text);
        line.appendChild(span);
      });
      pill.appendChild(line);
      groupEl.appendChild(pill);
      stage.appendChild(groupEl);
    });

    window.__timelines = window.__timelines || {};
    var tl = gsap.timeline({ paused: true });

    GROUPS.forEach(function (group, g) {
      var groupEl = document.getElementById("caption-group-" + g);
      var words = group.words || [];
      var next = GROUPS[g + 1];
      var isLast = g === GROUPS.length - 1;
      var start = Math.max(0, Number(group.start));
      var end = isLast ? DURATION : Math.min(Number(next.start), Number(group.end) + 0.3);
      if (end <= start) end = start + 0.01;

      // group on/off — exactly one group visible at a time
      tl.set(groupEl, { opacity: 1 }, start);
      tl.set(groupEl, { opacity: 0 }, end);

      // 3-state karaoke via className SETS — seek-safe (gsap.set applies on the
      // engine's frame-by-frame seek; .call callbacks would NOT fire).
      words.forEach(function (w, i) {
        var el = document.getElementById("caption-word-" + g + "-" + i);
        var at = Math.max(start, Number(w.start));
        tl.set(el, { className: "caption-word" }, start); // upcoming (also resets on reverse-seek)
        tl.set(el, { className: "caption-word is-active" }, at); // current
        tl.fromTo(el, { scale: 0.92 }, { scale: 1, duration: 0.16, ease: "back.out(2.2)" }, at);
        if (i + 1 < words.length) {
          var nextAt = Math.max(start, Number(words[i + 1].start));
          tl.set(el, { className: "caption-word is-spoken" }, nextAt); // demote when next activates
        }
      });
      if (words.length) {
        var lastEl = document.getElementById("caption-word-" + g + "-" + (words.length - 1));
        var lastSpoken = Math.min(end, Number(words[words.length - 1].end) + 0.1);
        tl.set(lastEl, { className: "caption-word is-spoken" }, lastSpoken);
      }
    });

    // full-span anchor so the sub-comp timeline spans the whole video
    tl.to({}, { duration: DURATION }, 0);
    window.__timelines["captions"] = tl;
  })();
</script>