Google · Video model
Veo 3.1 for ecommerce
Cinematic product video, generated with sound. Veo 3 is Google's video generation model, known for cinematic motion and for generating audio together with the picture. In Tolstoy it runs against your real catalog, so the output is a video of your product rather than a generic clip that happens to look like it.
Available tiers in AI Studio: Standard, Fast, Lite
Made in Tolstoy AI Studio — open one to see the prompt behind it, or browse the full gallery.
What Veo 3.1 is good at
Cinematic camera movement and lighting from a short prompt
Generates synchronized audio alongside the video
Holds a consistent look across a series of shots
Using Veo 3.1 in your store
Product videos from a single photo
Start from a packshot or lifestyle still and generate motion around it — the fastest way to give a PDP video coverage across a catalog that has none.
Paid social and ad creative
Generate multiple cuts of the same product for Meta, TikTok, and Pinterest, then publish the winners without a new shoot per variant.
Shoppable video for the storefront
Pipe Veo 3 output straight into AI Player widgets so the video is shoppable on the product page, not just an asset in a folder.
How to generate with Veo 3.1
-
Connect your catalog
Link your store so Studio can pull real product images, titles, and details — this is what keeps the output your product rather than a lookalike.
-
Pick the product and the shot
Choose the SKU, then describe the scene: setting, camera movement, mood, and how long the clip should run.
-
Generate with Veo 3
Select Veo 3 for the generation, or let Studio route automatically. Generate a few variations of the same brief and compare them side by side.
-
Publish where it sells
Push the winner to your storefront through AI Player widgets, or export it for Meta, TikTok, and email.
Prompting Veo 3.1
- Name the camera move explicitly — "slow dolly in", "orbit around the product" — rather than asking for something generic like "nice motion".
- Describe the light: soft window light, hard studio key, golden hour. Lighting drives whether the result reads premium or cheap.
- Say what the product must keep — logo, colour, texture, label — so details survive the generation.
- Because the model generates audio too, describe the sound you want (ambient room tone, footsteps, background music) or say to keep it quiet.
- Keep one idea per clip. Multiple unrelated actions in one prompt usually produce a muddier result than two separate generations.
How Veo 3.1 compares
| Model | Motion | Audio | Best for |
|---|---|---|---|
| Veo 3.1 | Cinematic, controlled camera moves | Yes — generated with the video | Hero, brand, and premium product film |
| Seedance 2.0 | Fast, dynamic, social-first | Not the model’s focus | TikTok, Reels, and paid social creative |
| Kling 3.0 | Physical, realistic, image-led | Not the model’s focus | Animating existing product photography |
| Sora 2 | Coherent multi-beat scenes | Yes | Story-led spots and campaign concepts |
Veo 3.1 FAQ
Can I use Veo 3 for ecommerce product videos?
Yes. In Tolstoy AI Studio, Veo 3 generates video from your product photos and prompts, using your catalog and brand references so the result matches the product you actually sell.
Does Veo 3 generate audio?
Yes — generating audio together with the video is one of the model's distinguishing features, so clips arrive with sound rather than needing a separate pass.
How do I access Veo 3 in Tolstoy?
Veo 3 is one of the models available in AI Studio — you can pick it per generation, or let Tolstoy route to it automatically. Start free to try it on your own products.
Can I publish Veo 3 videos to my storefront?
Yes. Generated video flows into AI Player widgets — shoppable feeds, PDP video, and galleries — and out to your ad and social channels.
Do I need a video team or editing skills?
Will the video actually show my product?
Yes — generations run against your connected catalog and product imagery, so the output features the SKU you selected rather than a generic stand-in.
Generate this on your own products
Connect your catalog and make your first video in minutes — no shoot, no editing timeline.
Other models
- Seedance 2.0 — Fast, motion-rich video for social-first commerce
- Kling 3.0 — Turn a product photo into believable motion
- Sora 2 — Coherent scenes built from a written brief
- Grok Imagine — Quick video and stills from the same model
- Nano Banana Pro — Edit product imagery by describing the change
- Seedream 5 Pro — Photoreal product and model imagery from a prompt
- ChatGPT Images — Brief-driven product stills that follow instructions
- All AI models