Audio price ladder for a 15-second Short: $0.7875 all in

A 15-second Short made from three 5-second Gemini Omni Flash 1.1 clips at 360p, one Music bed and one Timeline render costs $0.7875 on Sume: $0.5625 of footage, $0.125 for the bed and $0.10 for the render. Every audio step beyond that is a flat $0.01 job.

The list below is the audio part of the Sume price sheet as of 2026-10-08, so you can add or drop steps and see the total move.

The ladder

Omni's native audio is always on, so the footage already carries sound. The steps after it are choices.

Where the money goes

Footage is 71 percent of the total ($0.5625 of $0.7875). The bed is 16 percent and the render 13 percent. A Short that uses 720p Omni for the same three clips pays 15 x $0.125 = $1.875 for footage, and the total becomes $2.10. The audio cost does not move; the resolution does.

This is why the audio steps rarely decide a budget. The question is whether the bed fits, not whether it is affordable. Where sound is the point of the piece, spend on a second bed and compare, as in the A/B post on this blog.

What to skip

Skip the detach if you do not need the clip's sound apart from the picture. Skip the audio split unless the bed is longer than the cut: the Timeline soundtrack field takes loop, gain_db and a fade_out_seconds value up to 10, so a 15-second Short does not need a trimmed file at all. The render handles it.

A second look at the render line. Timeline bills per started output minute as a ceiling, so a 15-second render and a 59-second render cost the same $0.10. If you have 44 seconds of room, that is free space for a longer cut, a title card or a tail with the bed fading out. A 61-second render, on the other hand, is $0.20, so check the sum of your clips before you press go.

Where the numbers could change. Omni is $0.0375 per second at 360p and $0.125 at 720p in the catalog read for this post; the Music price is flat per generation. If you move to a different model, the audio rows keep their prices and only the footage line changes. For an example with Seedance 2.5 at 720p, the same 15 seconds would be 15 x $0.5778 = $8.667 of footage.

Do not add the video trim to get the length right if the three clips already add up: Omni runs 3 to 10 seconds per clip, so three 5-second clips are exactly 15.