One 15-second avatar script in 9:16, 1:1 and 16:9: cost of all three
Rendering one 15 s script in three aspect ratios is three jobs: $8.28 at standard, $11.025 at plus, $24.75 at max. Aspect ratio does not change the price.
Rendering one 15-second script in three aspect ratios on Sume means three separate jobs, and the price is the same for each: $2.76 at standard, so $8.28 for all three. Aspect ratio is a request field, not a price factor. The options are 1:1, 3:4, 9:16 (default), 4:3 and 16:9, all at 720p.
The three-job cost
Each job is billed on its own estimated length. Using the same avatar handle for each keeps the presenter consistent.
| Tier | One ratio (15 s) | Three ratios (45 s) |
|---|---|---|
| standard | $2.76 | $8.28 |
| plus | $3.675 | $11.025 |
| max | $8.25 | $24.75 |
Check the framing before paying three times
Avatar video previews show the first frame for an aspect ratio, and the preview stills do not depend on the tier. Use a preview for each of 9:16, 1:1 and 16:9 to check that the avatar and background sit well in each crop. Regenerating a preview is cheaper than regenerating a video.
If one ratio is wrong after rendering, you pay only for that job again: $2.76 at standard. The other two are unaffected.
Alternatives to three renders
A crop is $0.02, so a 9:16 render plus a crop costs $2.78, less than two renders at $5.52. But a crop removes picture, so it is a different frame, and a native 16:9 render is better than cropping a vertical file wide. Read the avatar video docs for the field list.
- Render 3:4 and crop to 4:5 with Video filter for a feed post, at $0.02 per crop.
- Render 9:16 once and reuse it for vertical placements only.
- Render 1:1 when one file has to serve a feed and a thumbnail slot.
Which ratio for which placement
Use 9:16 for vertical feeds and stories, 1:1 for square feed posts, and 16:9 for a website hero or a landscape player. The 3:4 and 4:3 options sit between them and suit portrait or landscape feed formats. Platform requirements differ: for example, TikTok non-Spark ads accept 9:16 from 540x960, 16:9 from 960x540 and 1:1 from 640x640, so a 720p render clears each of those minimums.
Spark ads accept mp4 and mov with no duration limit, and other ad formats accept up to 10 minutes, so a 15-second clip is well inside the length rules. Check the TikTok ad specification page before you upload.
Sources
Related posts
More in Sume Avatar 1.0
- Recast 3 old 10-second clips with the face swap beta: cost by tier
Face swap beta reserves 15 seconds of the tier price per run, so 3 runs cost $8.28 standard, $11.025 plus, $24.75 max.
- What to log for a likeness consent trail: five fields per request
Sume avatar and face swap requests carry an avatar_handle, a source URL, a quality, an Idempotency-Key and a job id. Log those five with the consent record.
- Which MCP grant lets an agent create an avatar? Write, no paid scope
On Sume's hosted MCP, avatars_create and the avatar video tools are paid tools that need the Write toggle at consent. There is no mcp:paid scope.
- Avatar video request rejected? Pre-flight these 6 inputs
Catch Sume Avatar 1.0 rejections before you submit: script vs video_inputs, the 4-60 second window, silence scenes, HTTPS media and caption style. A checklist.
Written by Sume