Merchant Center Product Studio video vs the Sume video API
Product Studio saves 720p, caps images at 32 MB and works in six countries. When a Sume video API request fits better, read from Google's page and Sume docs.

Product Studio in Merchant Center turns the product images you pick into a themed video inside Merchant Center, but it is limited to six countries, saves at 720p, and caps the combined images at 32 MB. If you need a different resolution, a model you choose, or a batch driven by code, the Sume video API is the alternative; if you only need a quick themed clip for a listing, Product Studio does that inside the tool you already use.
Google's side comes from About generating videos in Product Studio for Merchant Center (read 2026-10-11). Sume's side comes from its docs. The Sume docs I read do not list a Merchant Center connector, so the two do not exchange files automatically.
What Product Studio does, per Google
Figures below are quoted from the Google page (read 2026-10-11).
| Item | What the page says |
|---|---|
| Availability | Merchants based in Australia, Canada, India, Japan, the UK and the US |
| Orientation | Horizontal, vertical or square |
| Input size | All images in a video add up to 32 MB max |
| Output | 720p (1280x720) high-res; 240p (426x240) low-res for quick team sharing |
| Music | Theme music style (default), no music, or custom music |
| Text | Headline and subhead fields if the theme has them; Suggest Text can fill them |
| Editing | Edit video, change an earlier step, generate the preview again |
Where a themed template stops being enough
A theme is a fixed template: you pick images, text, colors, fonts and music, and the tool lays them out. That is quick for a catalog of simple listings. It is less suited when you want a particular camera move, a specific model, a start and end image you control, or a clip longer than a template gives you.
What the Sume video API gives you instead
Video Generation describes POST /v1/videos with a model, a prompt, an optional resolution, and frame_images for first-frame and last-frame image-to-video. The same page lists seedance-2.5 at 4 to 30 seconds and 480p, 720p or 1080p, so a request can ask for a higher resolution than Product Studio's 720p save.
For a catalog, Bulk runs lets one request queue 1 to 100 items at a concurrency of 1 to 16 against a Format, with a spend cap on each item. Per the docs, the Format catalog entries are read with GET /v1/formats/sume/{slug} before you call them.
- Use Product Studio for a fast listing clip in a supported country.
- Use the API when you need a chosen model, 1080p, a controlled start and end image, or a scripted batch.
- Either way, the finished file goes to Merchant Center by your own upload or link; check Google's own video rules before you submit.
Choosing without guessing
Run the same three products through both on a small trial. Compare the first second, text legibility on a phone, and how many manual steps each took. Product Studio's per-clip edit loop is convenient for one-offs; a queue is better once the list is long. For the Demand Gen side of product video, see Demand Gen dynamic product videos from Merchant Center. This post did not read Google's pricing or any limits beyond the page cited.
Sources
Related posts
More in Comparisons
- HeyGen enterprise writes rise to 30/s; how Sume limits submits
HeyGen raised enterprise limits: writes 30 per second, polling 1,500 per minute. Sume publishes no per-second number; it uses plan queues and rate headers.
- HeyGen instant voice clone audio in Sume? Only Sume-hosted audio
HeyGen's new instant voice clone can output TTS audio, but Sume's talking-still routes take only Sume-hosted audio up to 10 MB. What it blocks and what works.
- Is AI video 'Full HD' native or upscaled? Kandinsky 6.0 vs Sume rows
Kandinsky 6.0 renders 864x480 and adds Full HD with a plug-in. Sume's H3 Max 1080p is a latent refinement from 768p. What that means for price and detail.
- Is Kandinsky 6.0 Video on Sume? No: query the catalog by need
Sume lists no Kandinsky 6.0 id. Map each Kandinsky feature to a Sume request field, then filter GET /v1/videos/models for sound and a 5 s duration.
Written by Sume