Pipeline steps

Script scan: your cast, world, and voice blocks

The script scan ("Analyze Script" on the Characters & Assets step) reads your script and produces two things: the project's assets — every recurring character, environment, and object, each with a written description — and the voice blocks, the narration and dialogue units the voiceover step renders one by one.

What the scan extracts

• ·Characters — every recurring figure in the script, with a description used to render its reference image. Speaking characters also get a voice binding later.
• ·Environments — the places scenes happen in.
• ·Objects — recurring items that need to look the same across shots.
• ·Voice blocks — the script split into narration and dialogue units, each attributed to its speaker.

Re-running the scan keeps your assets

Re-analyzing the script adds any characters, environments and objects it finds that the project doesn't have yet. Assets you already have keep their descriptions, reference images and voices, and assets the new scan no longer finds are kept too — delete them yourself if you don't want them. Re-run the full scan when the cast itself has changed; otherwise use one of the paths below.

After a script edit: re-extract voice blocks only

If you edited the script's wording but the cast and world are unchanged, use Re-extract from Script on the voiceover step. It re-runs only the voice blocks; assets and their reference images are left untouched.

Manual asset management

The scan coexists with hand editing. You can add an asset yourself (name and description, plus a voice for characters), edit any asset's description, or delete assets you don't want — without re-running anything.

Models

The scan model is user-pickable — current options include Gemini 3.6 Flash, GPT-5.4 Mini, and GPT-5.4.

Once the scan is done, the next task is giving every asset a reference image — that's what unlocks the voiceover step.