Veo (Video Generation)

Veo is Google's video generation model. **Veo 3.1 generates 4K video up to 8 seconds with native audio**—including dialogue, sound effects, and ambient noise. Requires **AI Pro ($19.99/mo)**. Available in the Gemini app, Flow, and via API. Supports text-to-video and image-to-video with up to 3 reference images for character consistency.

Available on: Windows macOS iOS Android web API

Verified: 2026-02-22

Sources: https://deepmind.google/models/veo/, https://developers.googleblog.com/introducing-veo-3-1-and-new-creative-capabilities-in-the-gemini-api/, https://gemini.google/overview/video-generation/, https://developers.googleblog.com/veo-2-video-generation-now-generally-available/