Avatar video for YouTube Shorts: 9:16 or 1:1, up to 60 seconds

Avatar 1.0 makes 9:16 and 1:1 talking videos of up to 60 seconds at 720p, inside the Shorts window. Cost for 30 and 60 seconds, and one request.

3 min readSume
All posts

Sume Avatar 1.0 makes 9:16 and 1:1 talking videos of up to 60 seconds at 720p, which fits inside YouTube's Shorts rules: Shorts can be up to three minutes and square or vertical (read 2026-10-08, YouTube Help). A 60-second vertical avatar Short costs $11.04 on standard to $33.00 on max.

Avatar video supports five aspect ratios: 1:1, 3:4, 9:16, 4:3 and 16:9, with 9:16 the default. Pick 9:16 or 1:1 for Shorts.

Cost of a Short

Sume list price, no product image, read 2026-10-08
Lengthstandardplusmax
30 s$5.52$7.35$16.50
45 s$8.28$11.025$24.75
60 s$11.04$14.70$33.00

A square-format request

Switch aspect_ratio to 1:1 for a feed-friendly square; resolution is 720p at this time.

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: short-square-001" \
  -d '{
    "avatar_handle": "product_host",
    "aspect_ratio": "1:1",
    "quality": "plus",
    "script": "Three things I check before buying any desk lamp."
  }'

Longer than 60 seconds

One job stops at 60 seconds. For a longer Short, make several jobs with the same handle and join them with Timeline; the Shorts limit leaves room for three of them.

Captions

Optional inline captions burn into the finished MP4 from your script. They are an add-on priced into the avatar-video estimate, so check the estimate with captions on before you budget. Korean speech needs a Hangul style; Latin styles such as slam return 400 caption_hangul_text_latin_style.

Three jobs for a three-minute Short

Three 60-second jobs on plus are 3 x $14.70 = $44.10, and a Timeline render of the 180-second result adds $0.30 (the rate is $0.10 per output minute, rounded up). That is $44.40 before captions.

Sources

Related posts

More in Use cases

All Use cases posts

Written by Sume