Plan a drawn motion-graphics explainer on a voice-over

Turns a script of beats and ONE voice-over into ONE ready body for POST /v1/studio/edit: a fully drawn 9:16 explainer with no camera — the look of the "how it works" reels made in After Effects. Each beat is one layout of the scene explainer-scene (a big title whose marked words turn into an italic serif in the accent, a caption with its key word on an accent pill, and a layout: logo, versus (the old way crossed out), cards lit one by one, a counter rolling, a chat typing a request and ticking its steps, an app screen with stat tiles and task cards, devices, a graph around a centre, a site, an editor with a playhead, the end card with a countdown ring) on a dark, cream, accent or lavender plate with soft glows. Make the voice-over from the beats' say lines joined by spaces (POST /v1/ai/voice with timestamps: true) and send its url and words: every beat starts on the first word of its line (matched by the letters, so a name read as one word does not shift them), a soft whoosh on every turn, a music bed when you give one. Nothing is rendered here. Recipe: /skills/full-motion-explainer.md

Billing: Read request — the plan is free; the render is POST /v1/studio/edit (the beats are effect seconds of explainer-scene) · Rate limit: 60/min