AI Video Editing Flows

Effect #014 in our rendered series

Kinetic slam captions

Key words slam onto the screen with weight and settle, the punchy caption style of fast Shorts and ad hooks.

Real footage, with sound

1920x1080 file, 5.7 MB

Rendered by us at 1920x1080 over a shot from Tears of Steel (Blender Foundation, CC-BY 3.0). Expand plays the full 1080p file with the film's sound.

Edit in Premiere, Resolve or After Effects? Jump to editor templates. Making many versions of the same video? Use the code route.

Make this effect with

Built and tested by us

Other ways, not tested by us

Use it in a real edit

The demo above already plays the composition over real footage: the clip is a muted <video> layer under the graphics (the file plate.mp4 in the code below), and the film's sound is added to the finished file. Replace that file with your own clip and render again. To use the graphics in an editor instead, switch the background off and render a transparent MOV (an H.264 MP4 cannot carry transparency):

Render the graphics alone, with transparency
npx hyperframes render . -o overlay.mov --format mov --fps 24 --variables '{"plate":false}'

The routes in full

With Claude Code: the prompt we used

Rendered and tested by us in HyperFrames 0.8.10 on Nov 7, 2026.

Make a 5 second caption demo where each key word slams onto the screen with weight and a small settle, the way punchy Shorts captions do, never covering the speaker's face area in the middle third, with a transparent background option.

What changed since this prompt: the demo on this page is our second version, 6 seconds long, rebuilt on a shot from Tears of Steel with the same animation idea. The full composition below is the one we rendered; its build log lists every change.

Built by a Claude Code subagent (Sonnet) from the HyperFrames registry block caption-kinetic-slam, HyperFrames 0.8.10. Claude Code then checked the composition with hyperframes lint and hyperframes check before we rendered it.

What we had to correct (4 notes from the build log):

  • Lint run 1 (2026-11-05): 0 errors, 0 warnings.
  • What changed from the registry block: Registry block animates one big word at a time; changed to short 2 to 3 word lines in the top or bottom third so the face area stays clear. Replaced the translate-based centring with flex.
  • Decided against: using Math.random, Date, CDN GSAP, and any live measuring of text for layout.
  • v2 (7 Nov 2026): rebuilt on Tears of Steel footage (plate dlg_heart: 383.12 to 389.12 s, Celia, Thom with the robot hand, Celia) with the film's sound; each word slams in on the spoken word of 'You broke my heart. I know. You forgot me on Earth.' Key words in the accent colour. Sizes brought down to the caption range (88 px, key words 96 px). Audio starts mid-word (the film's own sound begins a quarter second before this shot), cut with a 30 ms fade (cut_dlg_heart.py).

With HyperFrames code

Rendered and tested by us in HyperFrames 0.8.10 on Nov 7, 2026.

Install the block and render
npx hyperframes add caption-kinetic-slam
npx hyperframes render . -o out.mp4 --fps 24

Settings you can change without rebuilding (pass them with --variables):

SettingNameTypeDefault
Key word colouraccentcolor#ffd400
Text size (px)sizenumber88
Caption positionpositionenumbottom
Show backgroundplatebooleantrue
Our full composition (index.html, 6 KB)
index.html
<!doctype html>
<html lang="en" data-composition-variables='[{"id":"accent","type":"color","label":"Key word colour","default":"#ffd400"},{"id":"size","type":"number","label":"Text size (px)","default":88,"min":76,"max":96},{"id":"position","type":"enum","label":"Caption position","default":"bottom","options":[{"value":"bottom","label":"Bottom third"},{"value":"top","label":"Top third"}]},{"id":"plate","type":"boolean","label":"Show background","default":true}]'>
  <head>
    <meta charset="UTF-8" />
    <meta name="viewport" content="width=1920, height=1080" />
    <link href="https://fonts.googleapis.com/css2?family=Anton&display=block" rel="stylesheet" />
    <script src="gsap.min.js"></script>
    <style>
      *, *::before, *::after { box-sizing: border-box; margin: 0; padding: 0; }
      html, body { width: 1920px; height: 1080px; overflow: hidden; background: transparent; }
      #root { position: relative; width: 100%; height: 100%; overflow: hidden; background: transparent; }
      #plate { position: absolute; inset: 0; background: radial-gradient(120% 90% at 30% 40%, #1b2335 0%, #0b0d12 70%); overflow: hidden; }
      #world { position: absolute; left: -200px; top: -120px; width: 2400px; height: 1320px; }
      .blob { position: absolute; border-radius: 50%; filter: blur(60px); }
      .b1 { width: 760px; height: 760px; left: 180px; top: 260px; background: #ffd400; opacity: 0.35; }
      .b2 { width: 900px; height: 900px; left: 1200px; top: 80px; background: #d4202c; opacity: 0.45; }
      .grid { position: absolute; inset: 0; background-image: linear-gradient(rgba(255,255,255,0.05) 1px, transparent 1px), linear-gradient(90deg, rgba(255,255,255,0.05) 1px, transparent 1px); background-size: 120px 120px; }
      #cap { position: absolute; inset: 0; z-index: 10; }
      .grp { position: absolute; left: 0; width: 100%; display: flex; flex-wrap: nowrap; align-items: flex-end; justify-content: center; gap: 0 34px; padding: 0 120px; opacity: 0; visibility: hidden; }
      .w { font-family: "Anton", sans-serif; font-weight: 400; text-transform: uppercase; display: inline-block; letter-spacing: 0.02em; line-height: 1; color: #fff; padding: 6px 0 10px; opacity: 0; text-shadow: 0 8px 0 rgba(0,0,0,0.45), 0 14px 30px rgba(0,0,0,0.5); transform-origin: 50% 70%; }
    
      /* footage plate (v2): real footage, pinned, no generated blobs */
      #plate { background: #000 !important; }
      #world { left: 0 !important; top: 0 !important; width: 1920px !important; height: 1080px !important; transform: none !important; }
      #world .blob, #world .grid { display: none !important; }
      #pv { position: absolute; left: 0; top: 0; width: 1920px; height: 1080px; object-fit: cover; }
      #scrim { position: absolute; inset: 0; background: linear-gradient(180deg, rgba(0,0,0,0) 45%, rgba(0,0,0,0.55) 100%); }
    </style>
  </head>
  <body>
    <div id="root" data-composition-id="main" data-start="0" data-duration="6.0" data-fps="24" data-width="1920" data-height="1080">
      <div id="plate"><div id="world"><video id="pv" src="plate.mp4" muted playsinline data-start="0" data-duration="6.0"></video><div id="scrim"></div><div class="blob b1" id="b1"></div><div class="blob b2" id="b2"></div><div class="grid"></div></div></div>
      <div id="cap"></div>
    </div>
    <script>
      window.__timelines = window.__timelines || {};
      (function () {
        const v = Object.assign({}, {"accent": "#ffd400", "size": 88, "position": "bottom", "plate": true}, window.__hyperframes.getVariables());
        const tl = gsap.timeline({ paused: true });
        if (!v.plate) document.getElementById("plate").style.display = "none";
        tl.fromTo("#world", { x: 0, y: 0 }, { x: -160, y: -50, duration: 6.0, ease: "none" }, 0);
        tl.fromTo("#b1", { x: 0, y: 0 }, { x: 140, y: -80, duration: 6.0, ease: "sine.inOut" }, 0);
        tl.fromTo("#b2", { x: 0, y: 0 }, { x: -120, y: 100, duration: 6.0, ease: "sine.inOut" }, 0);
        const GROUPS = [
          [["You", 0.04], ["broke", 0.46], ["my", 1.1], ["heart.", 1.4, 1]],
          [["I", 2.86], ["know.", 3.1, 1]],
          [["You", 4.04], ["forgot", 4.28], ["me", 4.74], ["on", 4.97], ["Earth.", 5.1, 1]],
        ];
        const ENDS = [2.24, 3.8, 5.82];
        const cap = document.getElementById("cap");
        GROUPS.forEach((g, gi) => {
          const grp = document.createElement("div"); grp.className = "grp"; grp.id = "g" + gi;
          if (v.position === "top") grp.style.top = "96px"; else grp.style.bottom = "80px";
          g.forEach(([text, , key], i) => {
            const w = document.createElement("span"); w.className = "w"; w.id = "w" + gi + "_" + i;
            w.style.fontSize = Math.round(v.size * (key ? 1.09 : 1)) + "px";
            if (key) w.style.color = v.accent;
            w.textContent = text; grp.appendChild(w);
          });
          cap.appendChild(grp);
          tl.set(grp, { visibility: "visible", opacity: 1 }, g[0][1] - 0.02);
          g.forEach(([, ws], i) => {
            const w = "#w" + gi + "_" + i;
            tl.fromTo(w, { opacity: 0, scaleX: 2.2, scaleY: 2.2, y: -40 }, { opacity: 1, scaleX: 0.94, scaleY: 0.94, y: 0, duration: 0.1, ease: "power4.in" }, ws);
            tl.to(w, { scaleX: 1, scaleY: 1, duration: 0.24, ease: "back.out(3.2)" }, ws + 0.1);
            tl.fromTo(grp, { y: 0 }, { y: 10, duration: 0.04, ease: "power2.out" }, ws + 0.1);
            tl.to(grp, { y: 0, duration: 0.16, ease: "power2.out" }, ws + 0.14);
          });
          tl.to(grp, { opacity: 0, duration: 0.14, ease: "power2.in" }, ENDS[gi] - 0.14);
          tl.set(grp, { visibility: "hidden" }, ENDS[gi]);
        });

        window.__timelines["main"] = tl;
      })();
    </script>
  </body>
</html>

With Remotion

We have not built this effect in Remotion. If you use it, read its licence first: Individuals (personal or commercial use), organisations or teams with a total headcount of 3 or less, non-profits, and anyone evaluating Remotion before commercial use. A company does not qualify merely because it is unprofitable. Everyone not eligible for the Free License needs a Company License. Remotion licence FAQ, checked Nov 4, 2026.

In your editor: Premiere, Resolve, After Effects, CapCut

We have not reviewed an editor template for this effect yet.

Variations

The same composition rendered again with different settings. Nothing was rebuilt.

Subtle: smaller text, pale gold key words{"accent":"#ffe9a8","size":76}
Bold: largest text, hot red key words{"accent":"#ff3b30","size":96}
Captions in the top third instead{"position":"top"}

Spec and test details

Engine
HyperFrames 0.8.10, GSAP 3.14.2 (local copy)
Length and frame rate
6 seconds at 24 fps, rendered at 1920x1080
Video files on this page
H.264: 1920x1080 for Expand (5807.1 KB), 1280x720 in the page (1693.4 KB), 640x360 in galleries (356.4 KB); the 1080p and 720p files carry the film's sound
Picture check
The 1080p file scores VMAF 99.45 against our render master and keeps 98% of its edge detail (measured by us with FFmpeg libvmaf and OpenCV)
Footage
Celia close-up, Thom with the robot hand on his face, Celia again; 'You broke my heart. ... I know. You forgot me on Earth.' (Tears of Steel, 6:23)
Tested in editors
None yet
Flash check
Passed: at most 2 general and 0 red flashes in any second. automated approximation of WCAG 2.3.1 on a 96x54 grid, whole loop including the restart; not a certification.
Licence
Composition adapted by us from the HyperFrames registry (Apache-2.0); text fonts from Google Fonts under the SIL Open Font License.
Last tested
Nov 7, 2026
Machine
Laptop: AMD Ryzen 7 7735U (8 cores, 16 threads), 31 GB RAM, Windows 11 Home; CPU rendering
Technical details: render times and file sizes
  • Render of the 6-second master: 40.7 s (2 render workers, on the laptop above).
  • full.mp4: 5807.1 KB
  • hero.mp4: 1693.4 KB
  • hero.webp: 32.6 KB
  • tile.mp4: 356.4 KB
  • tile.webp: 12.2 KB
  • Variation "subtle": rendered in 40.7 s, 350.9 KB
  • Variation "bold": rendered in 43.2 s, 355.7 KB
  • Variation "top": rendered in 44.7 s, 357 KB

Credits

  • Built from the HyperFrames registry component caption-kinetic-slam by HeyGen (Apache-2.0), adapted by us.
  • Fonts from Google Fonts, under the SIL Open Font License.
  • Footage: Tears of Steel, (c) Blender Foundation, mango.blender.org, licensed CC-BY 3.0. We cropped the shots to 16:9 and laid our graphics over them.
  • Editor templates and other routes on this page belong to their creators, who are credited on each card.

Related effects and jobs

Page checked on Nov 4, 2026.