TRStart creating
Menu

Text to video models

A text to video model turns a written scene into a moving clip. You describe the subject, what happens, how the camera moves and the light, and the model films it, often with sound. People use it for ad drafts, social clips and to see a scene before shooting it. 81 models do this job in the catalog right now. Each model's page shows its form and a price guide in US dollars.

Models

Page 2 of 4

Questions

How is a text to video model priced?
Video models usually charge per second of output or per video, and resolution, duration and audio can change the rate. Each model page shows its price guide in US dollars, and the studio shows the exact price for your settings before you generate. If a generation fails, the reserved amount goes back to your balance.
What should the prompt say?
Describe the subject, the action, the camera movement and the setting, in the order they matter. Some models also take a negative prompt, an aspect ratio or a duration; the model page lists every field.
Which model should I start with?
Pick two or three models whose examples look closest to what you want and run the same prompt on each, then compare the clip and the price. If the first frame must match a picture you already have, use an image to video model instead.
Can I call these models from the API?
Yes. Every model on this page has an API tab with its input fields, and the studio and the API share one account balance.

Other types

Found your direction?

Open the studio

We use analytics cookies. Privacy policy