What Explayner Does
Learn how Explayner creates videos from structured scene data with an AI director and deterministic 30 FPS browser rendering.
Overview & Architecture
Explayner creates videos from timed scenes. A scene can contain narration, text, emoji, ASCII diagrams, code, equations, shapes, lines, arrows, images, GIFs, transitions, animations, captions, music, and sound effects.
The key distinction between Explayner and traditional text-to-video AI tools is that the AI acts as the director, not a black-box pixel generator. It produces structured scene data that your browser validates and renders deterministically at 30 FPS. This gives you frame-accurate editability, zero timeline lock-in, and instant re-rendering without burning extra credits.
Supported Video Formats
Choose the aspect ratio tailored to your distribution channel:
| Format | Size / Orientation | Best For |
|---|---|---|
| Shorts | 720 × 1280 (9:16 portrait) | YouTube Shorts, TikTok, Instagram Reels, mobile-first demos |
| Full | 1280 × 720 (16:9 landscape) | YouTube tutorials, product walkthroughs, desktop presentations, course lectures |
Video + B-Roll mode seamlessly alternates between talking-head presenter footage and high-impact, full-screen graphic cutaways.