Veo 4

Combine text prompts with reference images, video clips, and audio files in a single generation, tagging each asset by name in the prompt.

Borrow motion, effects, camera movement, characters, scenes, or sound from uploaded material by describing what to reference in plain language.

Lip-synced dialogue, Foley effects, and background music are produced together with the picture, so no separate dubbing or syncing step is needed.

Characters, clothing, lighting, and text stay stable across cuts, supporting cohesive stories built from 4-15 second shots.

Extend clips, merge scenes, swap characters, or modify one segment while preserving the rest of the timeline.