Generate with Veo3 using Text Prompts

Follow this recipe to generate video using text:

The guide will recreate the following functionality in the Web UI via API.

Sample Request

curl --request POST \
     --url https://cloud.leonardo.ai/api/rest/v1/generations-text-to-video\
     --header 'accept: application/json' \
     --header 'authorization: Bearer <YOUR_API_KEY>' \
     --header 'content-type: application/json' \
     --data'
{
    "prompt":"a breathtaking, cinematic sequence of a massive crystal whale gliding through a vast night sky that behaves like a deep ocean. The whale’s body is sculpted from translucent, glimmering crystal—its surface faceted like a gemstone, catching moonlight and scattering it in radiant rainbow beams across the sky. Each movement creates soft refractions that dance across the clouds, making them ripple like bioluminescent waves.",
    "resolution": "RESOLUTION_720",
    "model": "VEO3",
    "isPublic": false
}

📘

Default Resolution

Veo3 only generates in 720p at an aspect ratio of 16:9 at dimensions 1280x720. height and width dimensions specified outside of this will not be accepted.

📘

Switch to Motion 2

To use Motion 2.0, remove the model parameter or set it to MOTION2.

Parameters such as frameinterpolation and promptEnhance are not compatible with Veo3.

Cost

The Text-to-Video endpoint costs 4000 API Credits per Veo3 video