Synthesia Layouts (100+ designs) vs Sume compose: stack or overlay
Synthesia Layouts ship 100+ scene designs in its editor. Sume compose builds one shot from one still and one video as stack or overlay. What to pick.

Synthesia's Layouts are a library of 100+ ready-made scene designs in its Editor. Sume has no design library: compose takes one still and one video and returns one MP4 with both on screen, using operation set to stack or overlay. Anything beyond those two arrangements is yours to build.
Synthesia facts are from its updates page (entry dated 9/2/2026); Sume facts from Timeline compose, read 2026-10-01.
What did Synthesia ship?
The entry describes Layouts as a library of 100+ ready-made designs right in the Editor, with instant theme previews and one-click swaps in Storyboard. It is an editor feature, so there is no API claim to compare against.
What does Sume compose give me instead?
Compose takes one still plus one video and returns one MP4 with both on screen at once. Required fields are operation (stack or overlay), image.url and video.url. Optional layout and output fields exist for placement and size; the docs describe the full field list.
| Question | Answer in the docs |
|---|---|
| Arrangements | stack or overlay |
| Inputs | One still and one video, both on media.sume.com |
| Output | One MP4; length comes from the video layer |
| Rate | $0.02 flat per job, confirm live in GET /v1/catalog |
| Sequencing and transitions | Stay on Timeline 1.0 |
How do I build a full scene sequence?
Compose makes one shot. Sequencing, transitions and the audio spine stay on Timeline 1.0: render a compose, then drop its video_url into a video[] slot. For a presenter with graphics, see talking head video with graphics.
Which one should I use?
If you want to pick from a catalog of scene designs by eye, that is Synthesia's editor. If you want a repeatable API step that places one still against one video, use compose. Import both files first with POST /v1/media-imports; an Idempotency-Key is required.
Sources
Related posts
More in Use cases
- Synthesia animated scene preview vs Sume first-frame stills
Synthesia previews one scene with a fully animated avatar. Sume previews are first-frame stills with no motion, approved before the full render.
- Synthesia avatar sharing vs Sume workspace-scoped avatars
Synthesia shares an avatar's base person with teammates or a workspace. Sume API keys are workspace-scoped, and avatars are referenced by handle.
- Target Circle Deal Days Oct 6-7: one master video, two cutdowns
Target Circle Deal Days run October 6-7 and Prime's event falls the same days. Cut one master video into a 15 s and a 6 s version with Sume's video-trim.
- Telegram custom emoji 100x100: make it from a 1024x1024 image
Telegram custom emoji are exactly 100x100, PNG or WEBP. 100x100 is far below GPT Image 2.5's size floor, so request 1024x1024 on Sume and scale it down.
Written by Sume