What you say to the agent
No special syntax — just describe it like you would to a person.
What it does, step by step
- 1
Give the agent a complete script or story idea, rather than co-authoring scene by scene.
- 2
It plans the scenes, sets up assets, writes the shot-by-shot prompts, saves the workflow, and starts generating — one deterministic chain instead of several separate tool calls.
- 3
You get back a saved, running video build, optionally scheduled to repeat if you ask for a recurring series.
What it needs from you
- •Your full script or story idea
What comes back
A saved video workflow with a run already in progress (or scheduled), generated straight from your script.
What it costs
Priced like a multi-scene video generation, shown before it dispatches.
Good to know
- This is the one-shot path for a script you've already written. For interactive scene-by-scene co-authoring, use the multi-scene movie capability instead.
Under the hood
This is what the agent actually calls when you ask for it — real tools from its live surface, not marketing copy.
create_from_scriptONE-SHOT deterministic path: freeform script/idea → saved Versely scene workflow → running render (and optional schedule). Server-side chains start_workflow_draft → asset setup → direct_scenes → save_workflow → run_workflow (and optionally schedule_workflow) with NO intermediate model turns. PREFER this over the manual draft→direct→save→run chain whenever the user supplies a complete script/story and asks to make it into a video. The multi-step chain remains for interactive co-authoring only. This is the deterministic anti-ghost-run path for complete scripts. Returns { workflow_id, run_id?, scenes_planned, scheduled?, next_run_at?, estimated_credits? } plus a user-facing summary. On failure, names the step that failed and reports any draft workflow_id.
The full tool behind it
See it done in a real workflow
Morning Matcha Routine
UGC-style wellness reel — a clean-girl creator walks through her actual morning matcha ritual, then cuts to a cozy animated hero shot of the finished iced latte.
TrendingNYC Street Interview
Photorealistic street-vlog interview — Riley works three different NYC corners at golden hour asking strangers one question: "What's the wildest thing you've ever done?" Three candid OTS/two-shot clips with locked character references, real handheld energy and native spoken dialogue. Vertical 9:16.
TrendingPrimo Protein vs Other Brand
Pixar-style 3D comparison ad — the confident PRIMO PROTEIN pouch faces off against the tired old rival brand's tub across 11 talking clips: pasture vs dusty pantry, herb garden vs toxic lab, clean American lab vs grimy factory, chocolate-milkshake CTA vs "wet sand." ~40s vertical reel with native character voices.
Or start from a one-tap template
Pet Hip Hop
Turn your pet into a couch-sitting hip-hop star.
Forgotten Cartoon
Turn any cartoon character into a decaying life-sized animatronic in an abandoned building — found-footage horror POV.
Mini Me
Turn yourself into a collectible vinyl figure on a desk, complete with packaging and 3D-sculpt monitor — then orbit it like a product reveal.
Frequently asked questions
What do I actually say to the agent to turn a script into a finished video?+
Just describe it in plain English — for example: "Here's my full script for a 30-second product ad — turn it into a finished video" The agent handles picking the right tool and model from there.
What does the agent need from me first?+
At minimum: Your full script or story idea. Anything else it needs, it asks for before running.
What do I get back?+
A saved video workflow with a run already in progress (or scheduled), generated straight from your script.
Does this cost credits?+
Priced like a multi-scene video generation, shown before it dispatches.
Anything I should know before asking for this?+
This is the one-shot path for a script you've already written. For interactive scene-by-scene co-authoring, use the multi-scene movie capability instead.
You can also just ask for
Ask your Versely agent to turn a script into a finished video
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync in a single app.