Veo 3.1

Google's flagship: cinematic video with synced sound

Google DeepMind's flagship video model. Creates 4–8 second clips in 720p or 1080p with native, context-aware audio — dialogue, sound effects and ambience. Control the shot with a first and last frame, or keep a character consistent with up to 3 reference images.

• Native audio with dialogue and lip-sync
• First + last frame control
• Up to 3 reference images for consistent subjects
• 16:9 and 9:16 in 720p or 1080p

Min. credits

160

Typical time

~100s

Max resolution

1080p