30-second avatar talking video: standard, plus and max cost

A 30-second Avatar 1.0 talking video costs $5.52 at quality: standard, $7.35 at plus and $16.50 at max when you send no product image. The per-second tier rates are $0.184, $0.245 and $0.55.

Sume's avatar video docs (read 2026-10-06) accept scripts that plan to 4 to 60 seconds, default to plus, and return 720p at 9:16 unless you set another aspect_ratio.

What does adding a product image cost?

A product_image raises the per-second rate, so the same length costs a little more.

How do I request it?

Send avatar_handle and a script (or video_inputs, not both). The planned duration is estimated from the script, so write for about 30 seconds.

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-30s-001" \
  -d '{
    "avatar_handle": "your-avatar",
    "script": "Your script here.",
    "quality": "standard",
    "aspect_ratio": "9:16"
  }'