Script to Storyboard: Turn Your Script into Shots with an AI Storyboard Generator

What does script to storyboard actually mean?

Script to storyboard is the step where a written scene becomes a numbered list of shots: what each shot shows, how wide it is, how the camera moves, who speaks and how long it lasts. Once the scene is broken down, art, camera and editing can all work from the same plan.

In Say Action, the AI storyboard generator reads your script and drafts an editable storyboard table. Each row is one shot with its shot number, duration, plot, dialogue, characters, shot size, camera and motion, emotion, lighting and atmosphere, sound, continuity notes, an image prompt for the frame and a motion prompt for the video.

How do you turn a script into a storyboard in Say Action?

Create a canvas, drop your script into a script node or hand it to the canvas agent, and ask for a shot breakdown by scene. The agent proposes the storyboard first and only writes it to your canvas after you approve, so nothing you already made is overwritten.

Every cell stays editable: reorder shots, change a duration, add a line of dialogue, switch a medium shot to a close-up, or bind a character reference image to a shot. Editing the storyboard does not use credits.

How do storyboard rows become frames and video?

Each row can be rendered directly: Nano Banana turns the image prompt into a keyframe, and Seedance 2.5 turns the motion prompt into video. You can also queue the whole storyboard as a batch. Bound character references and first/last frames travel with each shot to keep characters consistent from shot to shot.

Everything happens on one canvas, so the links between shots, references and finished clips stay visible, and you can redo a single shot without touching the rest.

Is the AI storyboard generator free?

Editing a storyboard on the canvas is free. Asking the AI to break down a script is a text generation and uses a small number of credits, and frames or video are charged by the model, resolution and length you pick. Every run shows its estimated credits before anything is charged.

Images, video and text share one credit balance, and failed generations are refunded automatically. If you already have your own model provider, you can connect it through BYOK.

Connect your own API channels and third-party relays

In model-channel settings, enter the Base URL and API key, then configure the protocol, model IDs and required headers from your provider's documentation. Check the image and video modes you need before generating. Paths, resolutions and first/last-frame inputs depend on the connected channel. An adaptation request for an unsupported channel is not a compatibility guarantee.

BYOK supports a custom API endpoint, model key and headers. For OneAPI, NewAPI or another relay, select the OpenAI, Gemini or Claude protocol that matches its actual API, then check model IDs and image/video endpoint support. Not every relay or private protocol works automatically. BYOK model calls have no platform model markup or platform generation-credit deduction; workspace access and provider usage are still billed separately.

Connect only trusted providers and use HTTPS in production. Custom requests are forwarded through the authenticated backend; required prompts, reference assets and credentials take part in the request. Never put API keys, passwords or secret-bearing headers in public canvases, screenshots or support requests.