Veo 3.1
Believable motion and light, with sound in the same take.
Veo 3.1 is the pick when hands, materials and light have to stay convincing for the whole clip. It makes 8 second clips at 16:9 or 9:16 with audio included, from a prompt, from a first and a last frame, or from up to 3 reference images. Fast, Quality and Lite tiers share one card, and a finished clip can be extended.
Best for
- Narrative beats where dialogue pacing and blocking matter
- Product shots with reflections, hands and real world interaction
- Transitions that have to start and end on exact frames
- Commercial cuts that will play on a big screen
Strengths
- Physics, lighting and materials that hold up across the take
- Audio included with every clip
- Three ways in: text, first and last frames, or up to 3 reference images
- Extend continues a finished clip from where it stopped
Limits
- Each generation is 8 seconds long.
- Aspect ratios are 16:9 and 9:16 only.
- There is no negative prompt, so phrase everything positively.
- Up to 3 reference images per request.
Practical tips
- 01
Iterate on Fast or Lite, then render the final on Quality.
- 02
Put spoken lines in quotes and say who speaks them, so the pacing lands where you want.
- 03
Use first and last frames when a shot has to hit a precise opening and closing composition.
- 04
Use Extend instead of a new generation when the same shot has to keep going.
Sample prompts
Copy one, paste it into Kubeez and change the details to fit your brief.
A barista in a small Lisbon cafe slides a cortado across the marble counter and says, "First one is on the house." Morning light through the window, steam from the cup, soft street noise outside. Slow dolly in.
Macro shot of raindrops hitting a glossy red car hood at night, city lights reflected in the paint, the camera slowly tilts up to reveal the empty street. Rain ambience, distant thunder.
Where it ranks
Position among the models available on Kubeez, from public blind votes, or the Kubeez team's own ranking for video editing and speech.
Veo 3.1
Believable motion and light, with sound in the same take.

