Criteo Retail Media onsite video: 720p, 15 s, a Sume avatar clip
Criteo onsite video asks for MP4 at 720p, 15 s recommended and 30 s max, in 16:9, 1:1 or 9:16. Sume avatar output is 720p, so script to 15 seconds.
What are Criteo's onsite video guidelines?
Criteo's Retail Media page lists MP4, 720p resolution, a 300 MB maximum and a recommended duration of 15 seconds, with 30 seconds as the maximum. Allowed aspect ratios are 16:9, 1:1 and 9:16. No bitrate requirement is stated on the page.
| Item | Criteo says |
|---|---|
| Format | MP4 |
| Resolution | 720p |
| File size | 300 MB maximum |
| Duration | 15 seconds recommended, 30 seconds maximum |
| Aspect ratios | 16:9, 1:1, 9:16 |
How does a Sume avatar job line up?
Resolution matches: avatar output is 720p. Three of the five avatar ratios, 16:9, 1:1 and 9:16, are Criteo's three. The job window is 4 to 60 seconds, so you must write the script to be short: a 15 second target is a script you can speak in about 15 seconds. Anything over 30 seconds will be too long for the placement even though Sume accepts it.
A 15 second clip with a product image at plus is 15 x $0.258 = $3.87; at standard, 15 x $0.194 = $2.91.
How do I add the product?
Pass product_image as a fetchable public HTTPS image URL, as in the product_image post. Then confirm the finished file with video inspect, since Criteo's page does not set a codec or frame rate here, and your retailer's ad ops may.
Make one job per ratio. Three ratios of one 15 second script at standard with a product are 3 x $2.91 = $8.73.
curl -X POST https://api.sume.com/v1/avatar-1.0/talking-video \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: criteo-sku1001-1x1" \
-d '{"avatar_handle":"your_avatar_handle",
"script":"This blender crushes ice in ten seconds.",
"product_image":"https://example.com/img/sku-1001.jpg",
"aspect_ratio":"1:1","quality":"standard"}'Sources
Related posts
More in Use cases
- Narration budget for a daily short-video channel: 30 videos a month
Thirty 750-character narrations a month cost $1.20 on Sume TTS with per-job rounding. The same characters are about $0.50 on MAI-Voice-2.1 and $0.34 on Flash.
- Dark mode hero image: one Ideogram 4.5 edit keeps the text
Make a dark-theme twin of a light hero on Sume with one Ideogram 4.5 edit: the background changes, the headline and layout stay, and the shape matches.
- Digital gift card art via API: generate the art, print the code
Make digital gift card artwork with GPT Image 2.5 on Sume, leave a clear text band, then print the amount and code in Pillow so no model ever types a real code.
- Product hero video: pin the first frame to your own packshot
Use frame_images with first_frame on sume/auto so a 6-second product video opens on your exact packshot, not a regenerated lookalike.
Written by Sume