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.
Sume lists Avatar Face Swap Beta at the Avatar Video no-product rate times the 15 second source-video maximum: $2.76 on standard (15 x 0.184), $3.675 on plus (15 x 0.245) and $8.25 on max (15 x 0.55). The catalog labels this a Beta contract estimate, so use it to size a budget, then read the real amount from the job.
| Quality | Rate per second | Arithmetic | Estimate |
|---|---|---|---|
| standard | $0.184 | 15 x 0.184 | $2.76 |
| plus | $0.245 | 15 x 0.245 | $3.675 |
| max | $0.55 | 15 x 0.55 | $8.25 |
Quality has no default here
On talking video, omitting quality gives plus. On face swap, quality is required and the endpoint does not use a default. A request without it is invalid, so you cannot drift into a more expensive tier by omission.
The other required fields are avatar_handle and a public HTTPS video_url. The endpoint rejects localhost, private-network, non-HTTPS, signed or private URLs and provider task URLs.
Source clip rules
The docs give the current plan as about 4 to 15 seconds with usable audio. The endpoint has no prompt, transcript, duration, aspect ratio or provider fields by design, so everything about the performance comes from the source clip. If you have a 40 second clip, cut it first, for example with the trim tools, and swap one 15 second piece at a time.
The 15 second figure is the ceiling the estimate is built on. Check the final charge for your own job in the usage record.
After it finishes
Use resource_status as the primary readiness signal and job_status when you poll. A completed resource exposes a video_url under media.sume.com. If a job is complete but the URL is empty, wait for the resource to be ready before you read it.
Beta means the terms can change. Do not build a billing promise to your own customers on the estimate; build it on the result you read.
Budget for a batch
For ten ad variants swapped from ten source clips on plus, the estimate is 10 x 3.675 = $36.75. On standard it is 10 x 2.76 = $27.60. Run one clip first and compare the real charge with the estimate before you queue the other nine.
Because the endpoint has no prompt field, each variant needs its own source performance. A swap changes the face, not the words, the setting or the length.
Keep the source clip's rights straight. If a creator supplied the clip, you need their permission to alter it with another face and to publish the result. Store the permission with the job id, the avatar handle and the source URL before you run the swap.
Do not confuse this endpoint with script-driven talking video. If you have words but no footage, the face swap cannot help you, and the talking-video route is the one to read first.
Sources
Related posts
More in Sume Avatar 1.0
- 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.
- Avatar script: 33 words = one 12 s clip, 34 words = two 7 s clips
A Sume Avatar 1.0 sentence of 33 words fits one 12-second clip. Add a 34th word and it splits into two 7-second clips. The numbers, with code.
- A 170-word avatar script in 34-word sentences plans 70 s: refused
Why a 170-word script of five 34-word sentences needs 70 seconds in Avatar 1.0, past the 60-second cap, and how to split it into two 35-second videos.
- Avatar video with a product image: the per-second price gap
On Sume Avatar 1.0 a product_image adds $0.010 to $0.030 per second by tier. For a 30-second spokesperson clip that is $0.30 to $0.90. Arithmetic inside.
Written by Sume