Studio
Examples Pricing
All guides

How to use Google Veo 3.1

Google's Veo: photoreal shots, spoken dialogue and 4K, and how to prompt for them.

Veo 3.1 is Google's highest-quality video model, known for photorealism, believable people and native audio including spoken dialogue. In GenKite you can use Veo 3.1 and the cheaper Veo 3.1 Fast online.

Veo 3.1 or Veo 3.1 Fast?

Both make 4, 6 or 8 second clips at 720p, 1080p or 4K, with optional sound and first and last frames. Fast costs much less, so use it to try ideas, then make the final version on Veo 3.1.

Step by step

  1. Open the studio and choose Veo.
  2. Write the prompt, or upload a picture to animate. Add a last frame to control the ending.
  3. Choose 4, 6 or 8 seconds and the resolution.
  4. Switch sound on if you want audio or dialogue (it adds to the cost), and generate.

Writing dialogue

Put the spoken line in quotation marks and say who speaks it:

A barista leans over the counter and says: "Your usual?" Warm café light, shallow depth of field, ambient chatter.

Keep each line short; an 8 second clip fits a sentence or two.

Prompts that suit Veo

Veo shines on photoreal people and places. Describe faces, light and texture plainly, and give each clip a single beat, because clips are short:

Handheld close-up of an elderly fisherman mending a net on a harbour wall at sunrise, gulls calling, sea breeze.

Is Veo 3.1 free?

New GenKite accounts get free credits with no card needed. Every clip shows its exact price before you generate, including the cost of sound.

See also: Veo vs Kling and Veo vs Seedance.