TikTok Symphony avatars skip shoes and hats: what to do instead
TikTok's Symphony avatar help page lists shoes, hats and sunglasses as unsupported product avatars. See the page's rules, then test an alternative on Sume.
If you sell shoes, hats or sunglasses, TikTok's Symphony product avatar will not do the job, because its help page lists those accessories as not supported. Your options are to show the item in a different way or to use another tool for that clip. On Sume you can pass a product image to an avatar video, but the docs do not promise how every accessory renders, so test one clip before you plan a batch.
What does TikTok's help page say?
The page does not state script length, duration or language limits, so none are given here.
| Topic | What the page says |
|---|---|
| Modules | Voiceover avatar and Product avatar |
| Unsupported product avatars | "Clothing accessories, such as shoes, hats, sunglasses bracelets, etc. are not supported" |
| Label | "An AI-generated label is added to all exported videos" |
| Review | Content goes through further moderation and policy review before it is cleared for publishing |
What can I try on Sume?
POST /v1/avatar-1.0/talking-video takes an optional product_image, and a scene that is either a prompt or a photo URL. Media must be public HTTPS URLs. The script runs 4 to 60 seconds and Avatar 1.0 speaks English only.
For an accessory, a person wearing or holding the item is the real test. Generate a preview first. It gives first-frame stills before the full render, so you can see how the item looks before you pay for the video.
{
"avatar_handle": "your_ready_avatar",
"aspect_ratio": "9:16",
"script": "These sunglasses are light enough to forget you have them on.",
"product_image": "https://cdn.example.com/sunglasses.png",
"scene": { "type": "prompt", "prompt": "Sunny street corner, handheld phone framing" }
}What if the preview looks wrong?
Do not publish it. Change the prompt, or use a still-based product clip instead, such as the product-usage-demo Format, which centres one real action with the item. Compare the result with your product photo for colour, logo and shape.
Whichever tool you use, read TikTok's current ad policies on AI-generated content before you upload. Its help page above says its own tool adds a label and reviews the content before publishing.
What should the shot list look like?
Ask what the avatar must show, then plan the rest of the ad around it.
- Open on the avatar speaking, with no product on the body.
- Cut to a product shot from your own photos.
- Close on a text card with the offer and the call to action.
- Keep each scene to a single idea.
Sources
Related posts
More in Use cases
- Audio version of an article with TTS: cost and the 20,000-char split
A 6,000-character article is one Sume TTS job at 29 cents. A 30,000-character one is two jobs plus a 1-cent concat, $1.45 total. Steps and code included.
- 4:1 banner into a 1:4 skyscraper: regenerate instead of cropping
A crop from 4:1 to 1:4 keeps 6.25% of the width. Send the banner as an input_reference with aspect_ratio 1:4 on Nano Banana 2.1 instead: $0.10 at 1K on Sume.
- 12 course module intros as 15-second avatar videos: $33.12
Twelve 15-second module intros with one reusable Sume avatar cost $33.12 on Standard, $44.10 on Plus and $99.00 on Max, plus $0.95 once for the avatar.
- 12 product clips with 12 voice lines: one join, one render, 15 cents
Twelve 75-character lines are 900 characters of TTS ($0.04275), one $0.01 audio join and a $0.10 render: $0.15275 for a 60-second product reel.
Written by Sume