53-second Avatar Video: $9.75 standard, $12.99 plus, $29.15 max

A 53-second Avatar Video costs 53 x $0.184 = $9.752 on standard, 53 x $0.245 = $12.985 on plus and 53 x $0.55 = $29.15 on max. Creating the avatar itself is a one-time $0.95. Sume estimates a script's length before accepting it, and the allowed estimated length is 4-60 seconds inclusive, so 53 seconds is inside the window with 7 seconds to spare.

The estimate matters because it sets the hold. A script that reads at 53 seconds is priced at 53 seconds, and a longer script can put the video above 60 seconds and out of range.

Three tiers, one script

The tiers share the duration rule and differ in rate. All figures are Sume's as of 2026-10-09.

How the length is estimated

The Avatar Video docs say Sume accepts scripts and multi-scene plans when it estimates the target video length, and the command-line docs repeat the 4-60 second bound for the estimate. If a script is close to either end, shorten or lengthen it before you submit rather than relying on the estimate to land inside the window.

Inline captions are a separate add-on in the avatar-video estimate, with their own length rule: Sume rejects an estimated duration of more than 60 seconds for inline captions. Standalone captions are a different job at $0.20.

A twenty-video month

Twenty 53-second videos on standard cost 20 x $9.752 = $195.04, on plus 20 x $12.985 = $259.70, and on max $583.00. With one new avatar, add $0.95. Because a paid job takes a seat, twenty videos on Pro fit in one submit pass (24 accepted), while Free would need four rounds.

Before a month of runs, read the Avatar Videos page for the current rules and confirm the live rates in the catalog.

Cost per spoken word

A 53-second script at a typical speaking pace is around 130 to 150 words, which is a rough guide only because pace varies by voice and language. On standard that is about 6.5 to 7.5 cents per word of finished video. The figure is useful for comparing script edits: cutting 10 seconds of script saves 10 x $0.184 = $1.84 on standard and $5.50 on max. Because the length is estimated before acceptance, edit the script, not the output, to save money.

Where the 60-second line sits

A script that estimates at 61 seconds is outside the 4-60 second window, so the practical maximum on standard is 60 x $0.184 = $11.04, on plus $14.70 and on max $33.00. If a script is longer, split it into two videos of up to 60 seconds each. Two 50-second videos on standard cost $18.40, which is also what 100 seconds would cost as a single video if it were allowed, so splitting does not change the price per second.