Three 15-second holiday avatar variants with a product: $11.61 on plus
Three 15-second holiday ad variants on Sume Avatar 1.0 with a product image cost $11.61 on plus, $8.73 on standard, $26.10 on max. How to test three hooks.
Three 15-second holiday ad variants on Sume Avatar 1.0 with a product image cost $11.61 on plus, $8.73 on standard and $26.10 on max. Use them to test three hooks with the same product and the same avatar, and keep the call to action fixed.
Rates are from the avatar price table (read 2026-10-06): $0.194, $0.258 and $0.58 per second with a product image.
Three hooks, one variable
Change one thing across the variants. Good candidates are the first sentence of the script: a gift angle, a deadline angle and a price angle. Keep the avatar, scene and product the same so the result says something about the hook.
| Tier | Per second | One variant | Three variants |
|---|---|---|---|
| standard | $0.194 | $2.91 | $8.73 |
| plus (default) | $0.258 | $3.87 | $11.61 |
| max | $0.58 | $8.70 | $26.10 |
Save money in the preview
Create previews first and approve the first frames. Then render the three on standard to see the delivery, and re-render only the winner on a higher tier with the quality override, which affects the final render only.
If the product image is wrong in the still, fix the inputs before any render.
Reading the results
Run the three variants for the same time, to the same audience, with the same budget, and let the ad platform split the traffic. Compare on one metric you chose in advance, such as the share of people who watch past the first five seconds.
Then take the winning hook and make the next round of three around it, changing the second sentence. Each round costs the same $11.61 on plus. The point is a repeatable loop at a small, known cost.
Before you launch
Check that all three scripts have a similar word count, around 42 words for 15 seconds. A longer script ends up crammed and a shorter one leaves dead air, and that would confound the comparison.
Name the files so you can tell them apart in the ad account, and keep the script for each in your own notes. When you pick a winner a month from now, you will want to know what it said.
Tradeoffs
Three renders tell you which script reads best, not which audience converts. Run them as an experiment on your own ad account and read the results there. Sume does not report ad performance.
Sources
Related posts
More in Use cases
- TikTok ad 500 MB cap and 516 kbps floor: file size by clip length
TikTok's ad page caps files at 500 MB and sets a 516 kbps minimum bitrate. For 15 to 600 seconds that is roughly 1 to 39 MB at the floor.
- TikTok ad minimum 540x960: Sume's 1080x1920 default clears it
TikTok's ad page sets minimums of 540x960 (9:16), 960x540 (16:9) and 640x640 (1:1). Timeline renders 1080x1920 by default, and width and height are settable.
- TikTok ad safe zones vs burned-in captions: anchor_ratio
TikTok says its safe zone varies with ratio, caption length and format. Sume caption design has an anchor_ratio to move a burned-in line.
- TikTok 6-slide 9:16 carousel: Qwen Image n=4 plus n=2 is 15 cents
A six-slide 9:16 slideshow takes two Sume image calls because n caps at 4. Qwen Image bills $0.025 per slide, so the set is $0.15. Code and cost table.
Written by Sume