Synthesia accepts WebP with transparency: what Sume avatar URLs need
Synthesia added WebP support on Sep 29, 2026, animated or static with transparency kept. Check what image URL rules apply when you feed Sume Avatar 1.0.
Synthesia's updates page lists WebP support on September 29, 2026, for animated or static images, with transparency preserved. That is a statement about Synthesia's editor. For Sume Avatar 1.0, the rule is about the URL, not the format name: avatar photo and product image inputs must be public HTTPS URLs whose content type matches the file, or the request is rejected before submission.
What Synthesia says
The entry is short: WebP images work in either animated or static form and transparency is kept. It does not describe limits, so read the live page before relying on it for a specific file.
| Fact | Value |
|---|---|
| Date | September 29, 2026 |
| Formats | WebP, animated or static |
| Transparency | Preserved |
What Sume checks
The media input rules reject localhost, private-network, signed and private URLs, and any URL whose content type does not match the file. The docs do not promise acceptance of every image format, so I would not assume WebP will pass; test with a small file first and fall back to JPEG or PNG.
For avatar creation the photo goes in input.photo.image_url. For videos, product_image and a photo scene are the optional image inputs.
curl -X POST https://api.sume.com/v1/avatar-1.0/generate \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"avatar_handle":"host_test","input":{"photo":{"image_url":"https://example.com/host.png"}}}'
A safe routine
Convert to PNG or JPEG if your tool exports WebP, serve it from a stable public host, and confirm the server sends the matching Content-Type header. Then preview the first frame before you render long.
Transparency is a design choice for a scene, not an avatar input; use a scene photo or prompt for backgrounds.
Sources
Related posts
More in Sume Avatar 1.0
- Tavus Griffin-Lite is not available: what to render today
Tavus says Griffin-Lite is a research preview for select testers only. If you need an avatar video this week, here is what Sume Avatar 1.0 renders today.
- Tavus Griffin single photo input vs a Sume photo avatar handle
Griffin works from one reference photo. In Sume you turn one photo into a named avatar handle once, then reuse it in every script. Steps, inputs and cost.
- Tavus Memory Stores vs Sume: personalizing avatar video per person
Tavus PALs now keep persistent memory per participant. Sume avatar videos are one-shot renders, so personalization is in the script you send. Here is the split.
- Introducing Sume Avatar 1.0
Sume Avatar 1.0 is a multi-agent orchestration system as a single avatar model.
Written by Sume