# Veo 3 image to video: animate a photo with sound

> Veo 3 image to video animates a still picture: your upload becomes the first frame, and Veo generates the motion and audio that follow. On GetVeo3 you upload one PNG, JPEG or WebP image up to 10 MB, describe the motion and sound, choose 16:9 or 9:16 to match the image, and get a 4, 6 or 8 second MP4 at 720p, or an 8-second one at 1080p. Pricing is the same as text to video, from 15 credits per second.

Upload a photo, illustration or product render as the first frame. Describe what moves and what we hear, and Veo 3.1 turns the still into a clip with its own soundtrack.

## At a glance

- **Input:** One PNG, JPEG or WebP image, up to 10 MB
- **Your image becomes:** The first frame of the clip
- **Shape:** 16:9 or 9:16; pick the one closest to your image
- **Length:** 4, 6 or 8 seconds at 720p; 8 seconds at 1080p
- **Sound:** Generated from your prompt, with the motion
- **Price:** Same as text to video, from 60 credits for 4 seconds with Lite

- Keeps your image's look
- Motion and sound from one prompt
- Photos, art and products

[Animate an image](https://getveo3.app/create)

## Image to video that respects your picture

- **First-frame control**: Your upload is the opening frame, so the subject, colors and style carry into the motion.
- **Motion and sound together**: Describe what moves and what we hear; Veo generates both, from footsteps to a spoken line.
- **Bring generated images to life**: Images from other AI tools make strong first frames, as long as you have the right to use them.
- **Vertical or landscape**: Choose 9:16 for portrait images and phone feeds, 16:9 for landscape photos and widescreen video.

## How to turn a photo into a Veo video

1. **Upload one image**: A sharp PNG, JPEG or WebP up to 10 MB, ideally already cropped to 16:9 or 9:16.
2. **Describe motion and sound**: What moves, how the camera behaves, what we hear and any dialogue in quotes.
3. **Match the shape**: Pick 16:9 for landscape images and 9:16 for portrait images, so little is cropped.
4. **Generate and download**: Review the clip, then reuse the settings to adjust the motion or sound.

## What Veo image to video does well

Because the first frame is fixed, image to video is how you animate something that must look right: a portrait, a painting, a product or a scene you designed with an image model. Veo continues the shot from that frame and adds sound that fits it.

- Portraits: a turn of the head, a smile, a short spoken line
- Landscapes: moving water, drifting clouds, shifting light and wind
- Artwork: illustrations and paintings that move in their own style
- Products: slow rotations, push-ins and reveals with tactile sound
- Old photos: gentle, natural movement as a keepsake

## How to write an image to video prompt

Describe the change, not the picture. The image already shows the subject, style and light, so spend the prompt on motion, camera and sound: “The steam rises, the camera slowly pushes in, a kettle starts to whistle.”

Gentle, physically plausible motion stays closest to the original. Big changes, such as new people entering or the camera turning around, ask the model to invent what the photo does not show, and the clip can drift from it.


## Inputs, shapes and limits

Veo renders 16:9 or 9:16 only. If your image is square or 4:3, crop it to the shape you want before uploading, so you decide what stays in frame, then pick the matching ratio in the generator.

In some of Google's own tools and APIs, Veo 3.1 can also take a last frame or reference images. GetVeo3 currently accepts one starting image per clip, used as the first frame; to steer the ending, describe it in the prompt. For 1080p, choose an 8-second clip; 4 and 6 second clips render at 720p.


## Related

- [Veo 3.1 video generator](https://getveo3.app/): Start from a prompt instead.
- [Prompt library](https://getveo3.app/prompts): Motion prompts with sound cues.
- [Veo 3.1 Fast and Lite](https://getveo3.app/veo-3-fast): Cheaper drafts of the same image.

## Veo 3 pricing: pay per second of video

- Starter: $19.99 / month, 2,000 credits
- Pro: $49.99 / month, 5,500 credits
- Studio: $99.99 / month, 12,000 credits
- Small: $9.99, 1,000 credits
- Medium: $29.99, 3,200 credits
- Large: $79.99, 9,000 credits

## Veo 3 image to video FAQ

### Can Veo 3 turn a photo into a video?

Yes. Upload the photo as the first frame, describe the motion and the sound, and Veo 3.1 generates a 4 to 8 second clip that starts from your image.

### Is Veo 3 image to video free?

No. Image to video uses purchased credits like text to video, and new accounts receive no free credits. The lowest-cost option is Veo 3.1 Lite, 120 credits for 8 seconds.

### Does image to video cost more than text to video?

No. The price depends only on the model and the length, whether you start from a prompt or an image.

### Will the face or product stay the same?

The clip starts exactly from your image. Small, natural motion keeps faces and products closest to the original; large movements can change details, so check logos and small text.

### Can I add dialogue to an animated photo?

Yes. Write who speaks and the line in quotes, for example: The woman looks at the camera and says, “Welcome home.” Keep it short enough to finish within the clip.

### Which images work best?

Sharp images with a clear subject and good light, already cropped to 16:9 or 9:16. Avoid heavy compression, tiny subjects and busy collages.

## Bring your picture to life

Upload an image, describe the motion and generate with purchased credits.

_Last updated 2026-10-06_