Skip to main content
Open HowWorks

Text to video. Write the scene.

Create AI video from a text prompt. Describe the subject, motion and camera without needing a starting image.

Describe what you want to create.
Model
Aspect ratio
Duration
Try a prompt:
Gothic Hall Dance
Gothic Hall Dance

Create a new five-second vertical dance shot inspired by the selected film. A small group of stylized adult dancers performs one coordinated movement in a tall gothic hall. Keep full figures readable, the camera steady and the rhythm clear. No captions, interface or watermark. This is a new scene brief.

13 s

Every single night, I pray that my [unclear] are sitting right. [unclear], my corset is so tight. Baby girl, [unclear], I feel like Nicole.

How it works

Try it now
  1. 01

    Say what you want

    A sentence or two is enough.

  2. 02

    Keep Auto, or set it

    Choose the settings that fit what you want to make.

  3. Gothic Hall Dance
    03

    Make it

    Start creating, then keep working with HowWorks.

Explore the possibilities

Gothic Hall Dance
Every single night, I pray that my [unclear] are sitting right. [unclear], my corset is so tight. Baby girl, [unclear], I feel like Nicole.

About

Text-to-video AI turns a written scene into a new clip. Give the shot a subject, a setting and one action: a curtain lifts as sunlight crosses a room, or a character reaches toward the lens. Describe the camera separately from the subject’s movement, and add an audio direction when using sound. Choose a model and supported duration that give the action time to read. Use Image to Video when a particular picture needs to establish the opening frame.

Questions

What should I put in a text-to-video prompt?

Name the subject and setting, one main action, the camera position or movement, and the light. For example: a paper boat crosses a puddle at dawn, filmed from water level with a fixed camera.

Can I generate a video without uploading anything?

Yes. This workflow starts from your written scene. If you need to begin with an existing picture, use Image to Video and add it as the start frame.

Should I describe several shots in one prompt?

For a first attempt, describe one shot and one main action so you can judge what worked. Plan separate shots when you need specific cuts or a sequence you can edit.

Can I choose the length and shape?

Use the duration and aspect ratio options available for the selected model. Plan the action for that length and compose it for its intended screen rather than relying on a later crop.

Will the result match every detail in my prompt?

Treat the result as something to review. Check subject details, motion, continuity and sound against the brief. Simplify or revise the request when an essential detail needs another attempt.