Veo3

Turning a text prompt or a still image into a short video with the dialogue, music and sound effects already in place is what Veo3 does.

Veo3 is an AI video generator built on Google's Veo technology, and it produces audio at the same time as the picture, so you skip the step of syncing sound afterward.

Lip-sync, tracking and realistic physics are meant to keep motion believable, and styles can be customized.

Veo3 works with Google's Imagen 4 and Flow, which is handy if you want image creation and video in one chain.

Casual and professional creators are both in scope.

The catches are access and length.

Access is currently limited to Gemini Ultra subscribers in the US and enterprise users through Vertex AI.

Clips top out at 5 seconds on the Basic plan and 10 seconds on Plus or Pro.

A commercial license comes with higher-tier plans, so check your tier before planning client work.