Longest Avatar 1.0 video is 60 seconds: $11.04 on standard

The longest single Avatar 1.0 talking video is 60 seconds, and it costs $11.04 on standard, $14.70 on plus and $33.00 on max without a product image. Sume accepts a script or multi-scene plan when it estimates the finished video at 4 to 60 seconds inclusive; longer scripts must be shortened or split into several jobs (Generate avatar video).

Billing is per second of video at a tier rate, so the 60-second case is simply sixty times the per-second price. A product image moves the rate up a little.

Cost of a full-length take

The request

quality is standard, plus or max; leaving it out means plus. The default aspect ratio is 9:16 and resolution is 720p.

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-60s-001" \
  -d '{
    "avatar_handle": "product_host",
    "quality": "standard",
    "aspect_ratio": "9:16",
    "script": "Paste a script that reads out to about sixty seconds."
  }'

When the script runs long

A script that Sume estimates above 60 seconds is refused, not trimmed. Split it at a natural break and submit two jobs. Inline captions have the same ceiling: an estimated duration over 60 seconds is rejected.

Splitting also lets you mix tiers. Use $0.184 per second for a bridge scene and $0.55 per second only for the shot that carries the offer.

• Under 60 s: one job, one handle, one face.
• Over 60 s: two or more jobs with the same avatar_handle, joined afterwards.
• Unsure about length: submit the shorter script first and check the finished duration.