Product image on a 60-second Avatar 1.0 job adds 51.6 credits at plus

Adding a product_image to a 60-second Avatar 1.0 video costs 51.6 more credits at the default plus quality: 1,021.2 instead of 969.6. At standard it is 39.6 more (768 instead of 728.4) and at max 118.8 more (2,295 instead of 2,176.2). The rate card charges per second of video, and a product image raises the per-second rate by a small amount.

So the product image is cheap compared with the video it rides on, roughly 5% of the plus total. Use it whenever the product has to be visible in the spokesperson's hands or beside them.

The numbers

Credits per second come from the Sume Avatar 1.0 pricing contract; the totals are multiplication by 60. Sume does not state a dollar figure in the docs I used here, so use the credit counts and your plan's credit price.

How to attach it

product_image is optional and must be a public HTTPS URL that Sume can fetch. Leave it out for a productless video. A 60-second script is the ceiling; Sume estimates the spoken duration from the script, and 4 to 60 seconds is accepted.

curl -X POST https://api.sume.com/v1/avatar-1.0/talking-video \
  -H "Authorization: Bearer $SUME_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: avatar-product-60s-001" \
  -d '{
    "avatar_handle": "store_host",
    "aspect_ratio": "9:16",
    "quality": "plus",
    "product_image": "https://example.com/gift-set.png",
    "script": "This is our winter gift set. It has three candles, a box of matches and a gift tag, ready to give."
  }'

Before you pay for 60 seconds

Test the product placement on a short run first. The first-frame approval post shows the preview route, which lets you see the frame before the full render. A 60-second job at max with a product image is 2,295 credits, so a wrong product photo is an expensive mistake.

• Use a clean product image on a plain background.
• Keep one avatar per final video.
• Burn captions inline instead of running a separate caption job.