HTML-based video composition with animations, captions, audio-reactive visuals, and scene transitions. Build video content as HTML with GSAP timelines and data-* attributes for timing; the framework handles clip visibility, media sync, and playback Create captions synced to audio, text-to-speech narration, audio-reactive animations (beat sync, glow, pulse), and animated text effects (marker sweeps, hand-drawn circles, scribbles) Add scene transitions (crossfades, wipes, reveals, shader transitions) between multi-scene compositions; every scene requires entrance animations and transitions between scenes Use variables to parametrize compositions — render the same source with different titles, colors, or content without editing HTML Supports sub-compositions loaded via external HTML files, design systems via design.md , and deterministic, fully seekable animations with no random or time-based logic

Agent Media OS, the single skill for every media need in a HyperFrames project. Resolve BGM, SFX, image, icon, brand logo, voice, color grade, or LUT into a…

Create AI avatar and talking head videos via inference.sh CLI. Recommended: P-Video-Avatar (fastest, cheapest, built-in TTS). Also: OmniHuman, Fabric,…

The HyperFrames composition contract — build one renderable project. Use for composition structure, the `data-*` timing attributes, `class="clip"`, tracks,…