Creative Methods
Shot List Generator: Build a Shot List from Your Script with AI
Use an AI shot list generator to turn your script into a shot list with shot size, camera movement, blocking, duration, lighting and sound for every shot, then render each shot as a frame or video in Say Action.
On this page
What is the difference between a shot list and a storyboard?
A shot list is the production table: every shot in order with its shot size, camera setup and movement, duration and key action. A storyboard focuses on what each shot looks like. In Say Action they are the same table, so you build the shot list first and then render a frame for each row.
That means no switching between a spreadsheet and a drawing tool. When you change a shot in the list, its image prompt sits in the same row and can be updated right there.
What does the AI shot list include?
Each shot is one row with the shot number, duration in seconds, plot, dialogue, characters, shot size, camera, motion and blocking, point of view, emotion, lighting and atmosphere, sound effects, time beats and continuity notes.
Every row also carries an image prompt, a video motion prompt and a negative prompt, so a shot can go straight to frame or video generation. Columns you do not need can be hidden.
How do you generate a shot list from a script?
Give your script to the canvas agent and ask it to break each scene into shots. The agent proposes the shot list first and writes it to the canvas only after you approve. From there you can edit shot sizes, insert shots and adjust timing directly in the table.
The AI breakdown uses a small number of credits, shown as an estimate before it runs. Editing the table by hand is free.
How do you turn the shot list into visuals?
Select the whole list or a few rows, render keyframes with Nano Banana, then generate video with Seedance 2.5. Character references and first/last frames bound to each shot help the same character look the same across shots.
Each generation shows its estimated credits first, failed runs are refunded automatically, and you can redo only the shot you are not happy with.
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.
Frequently asked questions
Can I use the shot list without generating images?
Yes. The list works on its own as a shooting or editing plan, and you can render frames for selected rows whenever you need them.
Can I use my own naming for shot sizes and camera moves?
Yes. Every cell is editable, and the agent follows the wording of the shots you have already written to keep the list consistent.
Are credits charged when a generation fails?
When the upstream explicitly reports failure, reserved credits are refunded; tasks with unclear network status stay pending review to avoid double settlement.
Can I connect OneAPI, NewAPI and custom headers?
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.