Veo 3 AI video generator
First and last frame video, multi-image reference and lip-synced dialogue
- Native audio
- Lip-sync
- First and last frame
- Up to 4K
Drag and drop, paste or click. JPG, PNG or WEBP up to 20 MB.
Mention files in the prompt as @Image1, @Video1 or @Audio1.
- Give each file one clear job: a face, an outfit, a location or a camera move.
- Mention files in order, like @Image1 and @Video1, so the model knows what to copy from where.
- Reference videos and audio work best between 2 and 15 seconds.
- Audio needs at least one image or video in the stack.
Text overlays appear with tips as the camera smoothly pans across the plants, enhancing the educational and calm tone.
The camera slowly pans upwards as the city awakens, capturing the gradual shift from artificial to natural light, evoking tranquility and wonder.
The camera tilts down to the steaming coffee as rays of sunlight dance around, creating an inviting and warm atmosphere.
The camera slowly zooms in on the figure, who turns and walks deeper into the shadows, heightening the suspense.
The camera circles the DJ as the lights pulse to the beat, capturing the electrifying, energetic ambiance of the dance floor.
The gadget rotates slowly, highlighting its cutting-edge design and technology while the camera gently zooms in to focus on its features.
The camera shakes slightly as hands organize the desk, placing items neatly and opening the notebook, creating an inspiring and relatable scene.
The colors pulse and shift rhythmically as the text pops in and out, creating an exciting and inviting introduction.
The camera glides through the forest, revealing hidden creatures and ancient ruins, building excitement and mystery.
The camera does quick cuts between different poses, capturing the energy and flair of urban fashion.
The camera dramatically swoops over the armies, building anticipation with the swell of the storm and distant battle cries.
The camera captures the motion of a squat with fluid movements, emphasizing form and guidance with upbeat energy.
What is Veo 3?
Veo 3 is the lip-synced dialogue model on NovaMotions AI. Characters speak your lines with matching mouth movement and native sound, in clips of 4, 6 or 8 seconds at 720p, 1080p or 4K. Start from text, from a first and last frame, or from up to 3 reference images, in 16:9 or 9:16.
- longest clip
- 8 s
- highest resolution
- 4K
- reference images per clip
- 3
What Veo 3 does well
The strengths worth knowing before you write your first prompt.
Lip-synced dialogue
Put a line in quotes and say who speaks. The character delivers it with matching mouth movement, natural timing and room sound.
Native audio by default
Dialogue, effects and ambience are generated with the picture and switched on by default, so scenes feel complete straight away.
Up to 3 reference images
Use Media mode to keep a face, an outfit or a location consistent with up to 3 images, mentioned as @Image1 to @Image3.
First and last frame
Set the opening and closing image of a shot, which keeps a talking scene framed exactly the way you planned.
Up to 4K
Render in 720p, 1080p or 4K, in 16:9 for widescreen or 9:16 for phones.
What you can make with Veo 3
Talking ads and testimonials
A customer, a founder or a character speaking straight to camera, with a clear line and natural delivery.
Dialogue scenes
Short exchanges between two characters, where lip-sync and timing make or break the moment.
Narrated explainers
An on-screen presenter delivering a key message in 8 seconds, ready to cut into a longer video.
How to use Veo 3
Four steps from an idea to a finished clip, all in the workspace above.
- 01
Choose how to start
Pick Media to build from reference files, Image to animate a first frame, or Text to describe the whole clip in words. You can switch modes without losing your prompt.
- 02
Add frames or references
In Media mode, upload up to 3 reference images and give each file one clear job. In Image mode, add a first frame and, if you like, a last frame. Text mode needs nothing.
- 03
Write the prompt
Describe the subject, the action, the setting, the camera move and the mood. Point to your files with @Image1 or @Video1 and put spoken lines in double quotes.
- 04
Set the shot and generate
Choose 4, 6 or 8 seconds, 720p to 4K, 16:9 or 9:16, and audio, check the credit cost on the button, then generate. Keep the best take or extend it with Continue from last frame.
Veo 3 vs Seedance 1.5 Pro vs Kling 3
Veo 3 and Seedance 1.5 Pro are the two lip-sync specialists. Veo 3 adds 4K and reference images, Seedance 1.5 Pro allows longer clips, and Kling 3 is the pick for cinematic shots up to 15 seconds.
| Compare | This modelVeo 3 | Seedance 1.5 Pro | Kling 3 |
|---|---|---|---|
| Best for | Lip-synced lines up to 4K | Longer talking scenes | Cinematic multi-shot clips |
| Ways to create | Media, Image, Text | Image, Text | Image, Text |
| Longest clip | 8 s | 12 s | 15 s |
| Highest resolution | 4K | 1080p | 4K |
| Aspect ratios | 16:9, 9:16 | 16:9, 9:16, 1:1, 4:3, 3:4, 21:9 | 16:9, 9:16, 1:1 |
| Media references | Up to 3 images | Not available | Not available |
| Native audio | On by default | On by default | On by default |
| Typical render time | About 3 minutes | About 3 minutes | About 3 minutes |
| Starting price | From 42 credits | From 31 credits | From 30 credits |
Veo 3 specs
These limits come straight from the workspace settings, so they always match what you can pick above.
- Ways to create
- Media references, Image to video, and Text to video
- Clip lengths
- 4, 6, or 8 seconds
- Resolutions
- 720p, 1080p, or 4K
- Aspect ratios
- 16:9 or 9:16
- Image input
- First frame plus an optional last frame
- Media references
- Up to 3 images
- Native audio
- Yes, on by default
- Prompt length
- Up to 10,000 characters
- Takes per run
- 1 to 4
- Typical render time
- About 3 minutes
- Starting price
- From 42 credits
Prompt examples for Veo 3
Press Try this and the prompt lands in the workspace above, ready to generate or tweak.
- Text to video
Founder's promise
A founder in a bright workshop wipes her hands on her apron, looks into the camera and says, "Every chair is built by hand, right here." Medium close-up, slow push-in, warm window light, the soft sound of sanding in the background.
- Text to video
Late-night diner
Two strangers sit at a diner counter at 2 a.m. The waitress refills a coffee and asks, "Long night?" The man sighs and replies, "Longest one yet." Static two-shot, neon glow through the window, coffee pouring and a humming fridge.
- Media references
Host welcomes viewers
The presenter from @Image1, in the studio from @Image2, waves and says, "Welcome back, today we're cooking with just three ingredients." Steady medium shot with a slow slide to the right, bright soft key light, light kitchen ambience.
Try thisUpload your files in Media mode first
Veo 3 questions
Short answers about modes, limits, credits and rights.
Ready to try Veo 3?
The workspace is at the top of this page. Generations start from 42 credits, and failed jobs return their credits automatically.
Still have a question?
Our team answers within one business day. The prompt guide covers references, camera moves, text and sound.
What is Veo 3?
Veo 3 is a video model on NovaMotions AI built for lip-synced dialogue. It makes 4, 6 or 8 second clips at 720p, 1080p or 4K from text, from a first and last frame, or from up to 3 reference images, with native audio.
How do I make a character speak?
Write the line in double quotes and say who speaks, for example the waitress asks, followed by the line. Keep it to one or two short sentences for an 8 second clip. Audio is on by default.
How many references can Veo 3 use?
Up to 3 reference images in Media mode, mentioned as @Image1 to @Image3. It does not take reference video clips or audio files.
Which lengths, resolutions and ratios are available?
Clips are 4, 6 or 8 seconds long, in 720p, 1080p or 4K, and in 16:9 or 9:16. The highest resolutions depend on your plan.
Can I turn off the audio?
Yes, switch audio off in the settings for a silent clip. Lip-sync needs audio, so keep it on for any scene with dialogue.
How do I make a scene longer than 8 seconds?
Split the dialogue into short clips and chain them. Open a finished clip and use Continue from last frame to start the next line from where the previous one ends.
Should I use Veo 3 or Seedance 1.5 Pro?
Choose Veo 3 for 4K and reference images. Choose Seedance 1.5 Pro when you need up to 12 seconds or formats beyond 16:9 and 9:16, like 1:1 or 21:9.
How many credits does a Veo 3 clip use?
It depends on the clip. Longer clips, higher resolutions and native audio use more credits. The exact amount shows on the Generate button before you spend anything, and the same balance works for video, images and music.
What happens if a Veo 3 generation fails?
Every credit goes straight back to your balance automatically. There is nothing to claim or report. Adjust the prompt or the settings and try again.
Can I use Veo 3 videos commercially?
Yes. Every plan includes commercial use and downloads have no watermark. You are still responsible for what you make, so avoid real people, logos or characters you do not have the rights to.
Explore more models
One credit balance works for every model. Switch any time from the sidebar.