Google · model workflow guide
Veo 3.1 Camera Prompts
Camera direction works best when it is tied to the subject action. One motivated move is usually easier to control than stacking several unrelated camera commands into a short clip.
How GenVideoKit structures Veo 3.1 prompts
Use coherent natural-language direction with explicit temporal flow from start state to end state. Describe subject action, camera behavior, lighting and environmental motion. When relevant, integrate dialogue, ambience and sound effects because this model family supports native audiovisual generation. Avoid conflicting camera moves and keep continuity physically plausible.
Text → videoImage → videoNative audioFirst / last frameExtension
Production shortcut
Use one dominant camera move per short shot. Tie the move to subject action and describe the desired end composition.
Reference pricing snapshot
$0.4 / second Tracking
Describe one coherent temporal camera move. Keep the subject at a consistent scale while the camera tracks parallel to the movement. Avoid sudden orbiting or reframing.
Push-in
Describe one coherent temporal camera move. Begin from a stable medium composition and make one slow push-in while the subject action remains readable.
Pull-back
Describe one coherent temporal camera move. Start close enough to establish the subject, then pull back smoothly to reveal more environment without changing screen direction.
Orbit
Describe one coherent temporal camera move. Use one restrained partial orbit around the subject while preserving body geometry, horizon stability and lighting direction.
Avoid stacking several independent moves such as “dolly in + orbit + crane + zoom” in one short shot unless the model and duration genuinely support that choreography.