AI avatar video aspect ratios: 5 options, 720p only on Sume
Sume Avatar 1.0 talking videos support 1:1, 3:4, 9:16, 4:3 and 16:9 at 720p. How to pick a ratio for Reels, ads, feed posts and web pages.
Sume Avatar 1.0 talking videos support five aspect ratios: 1:1, 3:4, 9:16, 4:3 and 16:9. The default is 9:16, and the resolution is 720p at this time. There is no 1080p or 4K option on this route, so choose the ratio by where the clip will play.
The supported options
These come from the Generate avatar video page, read 2026-10-08.
| aspect_ratio | Typical placement |
|---|---|
| 9:16 (default) | Vertical feeds, Shorts, TikTok |
| 1:1 | Square feed posts |
| 3:4 | Portrait feed formats |
| 4:3 | Older web and slide layouts |
| 16:9 | Web pages, landscape players |
Checking against platform rules
Two vendor pages give hard numbers for vertical video. TikTok's ad specifications (read 2026-10-08) recommend 9:16 with a minimum of 540x960 for non-Spark ads, and list 16:9 at a minimum of 960x540 and 1:1 at a minimum of 640x640. YouTube's Shorts help page (read 2026-10-08) says Shorts can be square or vertical and run up to three minutes.
A 720p 9:16 frame is 720 by 1280, which is above the TikTok 540x960 minimum. I am inferring that pixel size from the standard 720p vertical convention; the Sume page itself states only the ratio and that the resolution is 720p, so check the returned file with Video inspect before you upload a large batch.
- TikTok ads: 9:16 recommended, minimum 540x960.
- YouTube Shorts: square or vertical, up to three minutes.
- Sume: 9:16 default, 720p only.
A quick decision rule
Pick 9:16 for any vertical placement and keep it unless something forces a change. Pick 1:1 when one asset must serve a square feed and a story crop. Pick 16:9 only for landscape players. 3:4 and 4:3 exist for layouts that sit between these, so use them when a design or template asks for them by name.
Changing the ratio changes composition, so the preview stills are the cheapest place to check framing. Structural fields, including aspect_ratio, need a new preview, per the previews page.
Practical framing tips
Frame for the narrowest crop you expect. If a 9:16 clip may later be cropped to square for a feed, ask for a scene prompt that centers the speaker. Keep the product, if any, inside the middle of the frame, and avoid placing important text at the very top or bottom, where platform interfaces cover it.
Captions matter more in vertical formats. Inline captions burn into the final MP4 and use the spoken text, so they follow whatever ratio you chose. Pick a caption style before you finalize the ratio, and test with the preview stills, which never carry captions, plus one short full render.
Do not upscale an avatar clip and assume it equals a 1080p render. The Sume docs state that the resolution is 720p at this time, so any larger delivery size would be an upscale you add yourself.
Sources
Related posts
More in Sume Avatar 1.0
- AI avatar video length limit: Sume accepts 4 to 60 seconds
Sume Avatar 1.0 accepts scripts that it estimates at 4-60 seconds. What happens outside that window, and how to split a longer script into jobs.
- A 58-word six-sentence avatar script becomes a 10 s and a 12 s clip
How Sume Avatar 1.0 plans a 58-word script of six sentences: 27 words in 10 seconds, then 31 words in 12 seconds, 22 seconds total, and why the cut falls there.
- Avatar face swap Beta estimate: 15 seconds x tier = $2.76 to $8.25
Sume's Avatar Face Swap Beta reserves the 15 second source maximum at the Avatar Video tier rate: $2.76 standard, $3.675 plus, $8.25 max. What to check after.
- Avatar face swap beta limits: 4 to 15 seconds, quality required
Sume Avatar Face Swap is Beta: a public HTTPS source video of about 4-15 seconds with audio, a required quality tier, and no prompt or aspect options.
Written by Sume