TikTok Symphony Avatar virtual try-on: two Sume Formats
TikTok's upgraded Symphony Avatar joins voiceover, demos and virtual try-on. On Sume, sume-virtual-try-on and sume-product-usage-demo are two callable Formats.
TikTok's July 28 2026 product preview says the upgraded Symphony Avatar "brings voiceover, product demos, and virtual try-on into one workflow". On Sume there is no single avatar tool for all three; two catalog Formats cover the visual parts, sume-virtual-try-on and sume-product-usage-demo.
TikTok's text is from its Q3 product preview, read 2026-09-30. Format names are from the Format catalog.
What did TikTok announce for Symphony Avatar?
In Symphony Creative Studio, the upgrade is for more expressive, on-brand UGC-style content that narrates, demonstrates and showcases products with less production lift, without new shoots or reshoots. The snapshot does not list supported garment types or markets.
Which Sume Formats map to it?
Both slugs are on the catalog's callable list. The try-on recipe starts from a garment still and creates a 9:16 video of a creator changing into the garment, preserving the same face, body, room and camera angle. The usage demo recipe creates a 9:16 casual product-usage demo from a packshot.
| Capability | TikTok Symphony Avatar | Sume Format |
|---|---|---|
| Virtual try-on | Named in the preview | sume-virtual-try-on |
| Product demo | Named in the preview | sume-product-usage-demo |
| Voiceover | Named in the preview | Not a separate Format; describe it in your instruction |
What do I send?
Read the Format first with GET /v1/formats/sume/{slug}; its io profile says what input shape it expects, for example url_to_video. Then call POST /v1/formats/sume/{slug}/runs with the garment or packshot as an image attachment and your instruction. Try-on output depends on the garment and reference photos you provide, so review each result before it goes into an ad.
Where is a Shopify version of this?
See virtual try-on for Shopify for the store-side workflow.
Sources
Related posts
More in Use cases
- TikTok unoriginal content and the For You feed: AI batches
TikTok keeps reused material with nothing new out of the For You feed. How to plan templated Sume batches so every video carries something new of its own.
- TikTok video_cover_timestamp_ms: pick the cover frame in seconds
TikTok's Direct Post field video_cover_timestamp_ms takes milliseconds. Preview candidate frames with Sume video-frames, then multiply the chosen time by 1000.
- TikTok video ineligible for recommendation: AI content rule
TikTok keeps realistic content about public-interest matters out of the For You feed when it is not confirmed as AI or edited. What that means for Sume clips.
- Topaz Labs and Adobe: what Sume's image upscale API takes
Adobe completed its Topaz Labs acquisition on Sep 23, 2026, and Topaz stays standalone. If you need an upscale API, here is what Sume's accepts.
Written by Sume