Skip to content
Prism
Use cases

Animatic in After Effects with AI

An animatic in After Effects with AI starts with your boards and voiceover: ChatGPT, Claude or any MCP client connected to Prism places them in your open comp, one layer per shot, timed to the words.

Every After Effects animatic tutorial stops at "sync them with the visuals". The syncing is the job. Boards, a voiceover and a shot list that says which board belongs to which sentence are all the AI needs to lay the timeline out.

What you say, and what lands

You typeWhat appears in your comp
"Import the 24 PNGs in ~/boards in filename order, one layer each, bottom-first. Transcribe the VO layer, then start each board at the sentence marker it belongs to (boards 1–3 = sentence 1, 4–5 = sentence 2, and so on from the shot list I paste). Add a shot-number text layer top-left and a timecode burn-in. Hard cuts only."24 image layers in order, a [Transcript] guide layer with markers, each board's in-point at its sentence, a shot-number layer and a burn-in
"Shot 7 runs long. Hold it until the end of 'that is why we built it' and push everything after it."One in-point changed, later boards shifted with it
"Swap board 4 for the new PNG and keep its timing."One layer replaced, timing untouched
"Board 12 is missing. Generate a placeholder at the playhead: empty kitchen, pencil sketch."One image at the playhead, paid from your Prism AI balance

Test it on your own project. A Free account is enough to start: Sign up, then connect your AI and ask for this.

How to do it

1
Put the boards in one folder
Filename order is shot order. The voiceover goes on a layer in the comp.
2
Import them, one layer each
Ask for the folder in order, bottom-first, so shot 1 is at the bottom of the stack.
3
Transcribe the voiceover
Transcription places one marker per word on a [Transcript] guide layer above the audio. Ask for sentence markers too; the boards snap to those.
4
Paste the shot list
Which boards belong to which sentence. Each in-point is set to its sentence marker, each out-point to the next board's start.
5
Add shot numbers and a burn-in
A shot-number text layer top-left and a timecode burn-in, so notes come back with a time.
6
Re-time in words
"Hold shot 7 to the end of the sentence" moves one in-point and everything after it. Drag a layer by hand whenever that is faster.

Timing choices

ChoiceWhat to say
Frame rateThe rate of the final delivery; 24 fps for animation is usual
CutsHard by default; "6-frame dissolve between shots" if wanted
A board with no dialogue"Hold board 9 for two seconds"
A scratch voiceoverTime to it now; re-transcribe the final read and the in-points follow

A missing frame

Image generation makes one image per run at the playhead, a Prism AI capability paid from your balance. Use it for a placeholder plate or one missing board, not the set.

What it needs

After Effects2024, 2025 or 2026, macOS or Windows
AI clientany MCP client: ChatGPT, Claude, Claude Code, Cursor, Codex and others
Plana Free account covers import and timing (MCP actions); transcription and image generation are Prism AI capabilities, Pro, paid from your balance

What it does not do

It does not draw your storyboard or break a script into shots. The boards and the shot list are yours; Prism places and times them.

Common questions