01 / 06
Start with words
Describe the character, action, and setting, then expand a sentence into a shot with space and rhythm.
Create
Veo 3.1
Duration
Aspect ratio
Resolution
Videos usually take a few minutes. Keep this page open until completion.
Generated video
01 / 01
Turn a written idea or a single image into a complete shot with motion, sound, and rhythm. Shape the duration, frame, and finish.
CREATE WITH VEO 3.1
Nano Banana 2 brings Veo 3.1 video and native audio into one focused creative workspace. Write the idea or upload a still, then let the shot unfold.
Text / image
two creative starting points
4 / 6 / 8 sec
control the pace
16:9 / 9:16
made for every screen
720P / 1080P
preview or final output
Frame 01 · 00:00
NATIVE AUDIO
BUILT FOR MOTION
A convincing shot needs movement, timing, and sound to work together. Veo 3.1 builds continuous visuals from text or images while bringing camera direction, dialogue, ambience, and style into the same generation.
NANO BANANA 2 VIDEO
One workspace for concept tests, social content, campaign assets, and storyboards.
01 / 06
Describe the character, action, and setting, then expand a sentence into a shot with space and rhythm.
02 / 06
Use a still as the opening frame and extend its subject and composition with motion, camera work, and change.
03 / 06
Create dialogue, ambience, and sound effects with the visuals so audio never feels added as an afterthought.
04 / 06
Choose 4, 6, or 8 seconds for anything from a sharp visual hook to a complete emotional beat.
05 / 06
Move between 16:9, 9:16, and Auto so the same idea feels native in landscape or portrait.
06 / 06
Use 720p to explore a direction quickly, or choose 1080p for more detail and post-production room.
MADE TO MOVE IDEAS
Connect creative validation, previsualization, and content production so your team can see an idea come alive sooner.
Turn product benefits, brand mood, and campaign ideas into moving creative.
Create vertical clips, opening shots, and visual hooks for mobile platforms.
Test scenes, camera positions, character movement, and pacing before a shoot.
Translate abstract concepts into rhythmic, cinematic shots with sound.
CHOOSE YOUR TEMPO
| Comparison | Veo 3.1 | Veo 3.1 Fast |
|---|---|---|
| Primary goal | Higher visual fidelity and creative control | Faster generation for high-volume creation |
| Best for | Cinematic shots, complex action, final assets | Ad variants, social content, batch testing |
| Native audio | Supported | Supported |
| Choose it when | Quality and consistency matter most | Speed and output volume matter most |
ONE CREATIVE FLOW
Write the idea or upload an image to establish the opening frame.
Add action, camera, and sound, then set the duration, ratio, and resolution.
Preview the result, download the video, or adjust the prompt for another take.
DIRECT THE SHOT
Describe what the camera can see and hear before adding style. Write the prompt like an executable shot plan instead of a list of abstract adjectives.
Shot formula
Subject & action + setting + shot & camera movement + light & style + dialogue & ambience
Example prompt
A red vintage convertible drives along a coastal road at golden hour. Low-angle side tracking shot, slowly pushing toward the driver, warm cinematic light, ocean wind moving her hair. Distant waves and a soft engine hum. The driver says quietly, “We leave before sunset.”
FAQ
Clear answers about creation modes, video settings, and the generation flow.
Veo 3.1 is a new-generation AI video model that creates coherent video from text or an input image, with synchronized dialogue, ambience, and sound effects.
Start directly from text or upload one image as the opening frame. Image mode preserves the original subject and composition where possible, then follows your prompt for motion, camera direction, and sound.
Choose 4, 6, or 8 seconds, 16:9 or 9:16, and 720p or 1080p. Image mode can also use Auto to naturally preserve the composition of the opening frame.
Yes. Veo 3.1 natively generates synchronized dialogue, ambience, and sound effects. Include spoken lines, sound sources, and the intended sonic mood in your prompt.
Yes. Choose 16:9 for widescreen content, 9:16 for mobile-first short video, or Auto to infer the best format from your starting image.
Use a concrete structure: subject and action, setting, shot size and camera movement, lighting and visual style, then dialogue and ambient sound. Specific camera language is usually more useful than abstract adjectives.
Veo 3.1 prioritizes visual fidelity, camera control, and consistency in complex scenes. Veo 3.1 Fast prioritizes speed for ads, social content, and high-volume creative testing.
Videos usually complete within a few minutes. Follow the live status in the result area, where the finished video appears automatically without repeated refreshes.
Yes. The finished video appears directly in the result area, ready to preview and download for content production, creative presentations, or further editing.
Keep the subject, setting, and style, then adjust the action, camera direction, aspect ratio, or duration to explore new pacing and compositions.
Nano Banana 2 Video
Open the generator and hand the picture in your mind to Nano Banana 2.