Google DeepMind logoGoogle DeepMindVideo

Veo 3.1

Google's cinematic video model with native audio and up to 4K output.

Playground

Video Generator

Model

Veo 3.1

No videos generated yet

Enter a prompt and click Generate to create your first AI video.

About this model

Capabilities & specifications

Input
Text · Image · Video
Output
Audio · Video

Veo 3.1 supports cinematic video, native audio and reference-driven creative controls. Google's guide documents 4, 6 and 8 second outputs with resolution-dependent restrictions. Gemini API preview endpoints were retired; check the currently offered enterprise endpoint before integration.

  • Cinematic video
  • Reference control
  • Audio-visual generation
Video generation

Examples

Veo 3.1 integration demonstration excerpt

Model output documented by the source.

Third-party demonstration

Questions and answers

Where do Veo 3.1 specifications come from?

The references below identify the sources for this model’s capabilities. Confirm current access, request limits and pricing with your service provider before integration.

Where do Veo 3.1 specifications come from?

Things to consider

Review generated results before use. Available modes and request limits depend on the service you choose; check the linked documentation before integration.

Model information sources

  • Veo 3.1 reference