Native audio
Generate video with audio cues that match the visual scene.

A Gemini video model for cinematic clips with native audio, image guidance, and more controlled start-to-end visual direction.

Use Veo 3.1 when the shot needs strong visual direction, native sound, and reference-aware framing.
Generate video with audio cues that match the visual scene.
Use images to steer starting composition, subject identity, and visual atmosphere.
Useful for planned transitions and shots that need a clearer destination.
Veo 3.1 works best when the prompt describes how the shot starts, what changes, and how it should end.
Describe the first frame or use an image to anchor it.
Name the subject action, camera move, pace, and audio texture.
For start-end work, verify that the final composition matches the intended destination.
Use these notes as production guidance inside Creativ Studio. Provider availability and exact limits can vary by account, region, and model rollout.
High-quality video with audio
veo-3.1-generate-preview
Text and images
720p and 1080p in Creativ Studio
Preview availability and limits can vary by Google account and region
Use these as starting shapes, then swap in your own subject, references, and constraints.
A slow tracking shot through a greenhouse after rain, leaves dripping, soft morning light, gentle water sounds, calm cinematic pacing.
Begin on a close-up of a sealed invitation, then the camera pulls back to reveal a candlelit dinner table, soft room ambience.
Yes. Veo 3.1 is designed for video generation with native audio output.
Yes. Images can guide the starting frame, composition, and subject appearance.
Use Veo 3.1 Fast when you want lower latency for draft exploration.