21 Shorts a week at 59 seconds: render and captions cost $6.30
Three Shorts a day for a week, each held to 59 seconds: one Timeline render ($0.10) and one caption job ($0.20) per Short comes to $6.30.

Finishing 21 Shorts a week at 59 seconds each costs $6.30 on Sume: each Short needs one Timeline 1.0 render at $0.10 (59 seconds rounds up to one minute) and one standalone caption job at $0.20, so 21 x $0.30 = $6.30 (read 2026-10-08). Keeping every Short under one minute is a choice, not a limit, and it avoids one specific YouTube risk described below.
Why 59 seconds
YouTube's Shorts page (read 2026-10-08) says a Short can run up to three minutes, in a square or vertical frame. It also says a Short over one minute with an active Content ID claim is blocked globally and loses monetization. A team that uses licensed or trending audio can sidestep that rule by staying at or under 59 seconds. If your own recording and your own generated music carry no claim, longer cuts are fine.
- Shorts up to three minutes; square or vertical
- Over one minute plus an active Content ID claim: blocked globally and loses monetization
- Audio Library songs: usable up to 90 s in a 3-minute Short, some limited to 60 or 30 s
The weekly bill
Both rates are fixed. Timeline 1.0 charges $0.10 per ceil(output minute) and reserves ceil(audio.duration_seconds / 60) minutes. The caption price applies to videos of up to 60 seconds, so a 59-second cut qualifies.
| Line | Arithmetic | Cost |
|---|---|---|
| Timeline 1.0 renders | 21 x $0.10 | $2.10 |
| Standalone captions | 21 x $0.20 | $4.20 |
| Total | $2.10 + $4.20 | $6.30 |
| Per Short | $0.10 + $0.20 | $0.30 |
Set it up once
Store the output block and the caption style as constants so every Short matches. The default output is 1080x1920, and if you omit output.fps the render follows the source frame rate; set it only if your sources mix rates, because a mismatch makes Sume repeat or drop frames and warn with output_fps_resamples_sources. Use output.fade_out_seconds (0 to 5) to end each Short cleanly.
Use the plan endpoint on the first Short of the week. It is unbilled and returns billable_minutes, so you see 1 minute and $0.10 before the real render. A 59.9-second spine is still one billed minute; a 60.1-second spine is two, so the rounding is the thing to watch.
{
"audio": { "url": "https://media.sume.com/artifacts/artf_demo/mon-vo.wav", "duration_seconds": 59 },
"video": [
{ "source_url": "https://media.sume.com/artifacts/artf_demo/mon-a.mp4", "start": 0, "duration": 30 },
{ "source_url": "https://media.sume.com/artifacts/artf_demo/mon-b.mp4", "start": 30, "duration": 29,
"transition": { "type": "fade", "duration": 0.25 } }
],
"output": { "width": 1080, "height": 1920, "fade_out_seconds": 0.5 }
}Sources
Related posts
More in Use cases
- 250 product photos to 5-second 1080p clips with Omni: $234.38 on Sume
250 SKUs as 5-second image-to-video clips cost $234.38 at 1080p, $156.25 at 720p and $46.88 at 360p on Sume's Omni row. A draft plan brings it to $103.13.
- 28-minute podcast episode on Sume: narration, bed, render = $4.125
A 28-minute narrated episode costs about $4.125 on Sume: two TTS requests ($1.20), one Music 1.0 bed ($0.125) and a 28-minute Timeline render ($2.80).
- Vidu Q4 takes 3 audio references; which Sume video models take one?
Sume does not list Vidu Q4 Preview. Seedance 2.x, Wan 3.0 and MiniMax H3 accept reference audio; Gemini Omni Flash 1.1 does not. Prices for 15 seconds.
- A 3-minute Short with a ducked music bed: $0.425 on Sume
YouTube Audio Library songs cap at 90 seconds in a 3-minute Short. Generate one Music 1.0 track for $0.125 and render with ducking for $0.30.
Written by Sume