Turn a text prompt into your next video shot.

A prompt formula you can reuse

Write five parts: subject, action, environment, camera and light. “A silver robot” names the subject; “carefully sets down a glass sphere” gives it an action. A dark studio, a slow push-in and a soft rim light complete a coherent shot. Specific actions are more useful than a long list of quality adjectives. Prompts can contain up to 2,000 characters.

From a script to individual shots

Split a script into visible actions before generating. A ten-line voice-over is not automatically a video brief: identify what the viewer should see in each scene. Generate each shot separately, review it and assemble clips in an editor. FreeVideo AI does not automatically create narration, captions, storyboards or a multi-scene edit.

Cinematic and social-video use

For a cinematic test, keep one camera move and describe lighting that belongs to the setting. For vertical social footage, keep the main action central so you can crop in an editor. The studio’s portrait output is 512 × 896, not native 1080 × 1920. Add captions and sound after downloading; generated clips are silent.

Cost and iteration

Text-to-video costs 6 credits for each 5-, 10- or 15-second task. A new Google account’s 60-credit grant can cover up to 10 text tasks before other usage and expires after 30 days. Start short, then adjust one element of the prompt at a time. Save prompts alongside successful outputs so you can understand which changes helped.

A prompt to start with

A silver robot carefully sets down a glass sphere on a dark studio table, slow push-in from a medium shot, soft rim lighting reflected in the glass, one continuous shot, no cuts.

Use this as a starting point, then adjust one action or camera instruction at a time. It is a prompt example, not a guarantee of a specific result.