Loading page
Model guide · Video · Google DeepMind
Image-to-video from a locked still, plus native audio
Image-to-video with synchronised speech, which makes it the shortest path from a character sheet to a talking clip. The still you feed it is doing all the identity work.
What it is good at
Where it stops
Generated speech carries its own disclosure obligation on top of the image one. Both, not either.
Routes it can take you on
The syntax
This is Maya Rao from the cast, rendered into Veo's own syntax. Square brackets are the things only you have.
Image: [url of your approved reference frame] Action: [what moves — keep it small] Dialogue: "[one line of dialogue]" Camera: slow push in | Aspect: 9:16
Build your own in the studio and this same block comes back filled with your persona instead — same structure, your locked line, your seed.