YouTube Shorts ad under 60 seconds: stitch clips with Timeline
YouTube suggests Shorts ads under 60 seconds. Sume Timeline 1.0 stitches clips into one MP4 at $0.10 per output minute, so 60 seconds costs $0.10.

A YouTube Shorts ad that is 60 seconds or less costs $0.10 to assemble on Sume, because Timeline 1.0 bills $0.10 per output minute rounded up. YouTube's help page, read on 2026-10-07, says Shorts ads are under 60 seconds recommended. Timeline takes an audio spine plus an ordered list of video slots and returns one MP4, with a default output of 1080 by 1920, which is already the vertical frame Shorts use.
What YouTube states and what Sume bills
YouTube's page gives a length note for Shorts ads and no technical file specs in the text we retrieved. The Sume side is exact: the public Timeline rate is $0.10 per ceil of the output minute, and the plan route tells you the billable minutes before you spend anything.
| Output length | Billable minutes | Timeline cost |
|---|---|---|
| 15 seconds | 1 | $0.10 |
| 45 seconds | 1 | $0.10 |
| 60 seconds | 1 | $0.10 |
| 61 seconds | 2 | $0.20 |
Stitching a Short from clips
Generate the shots separately, since each model has a maximum duration, and assemble them on a Timeline. The program needs audio.duration_seconds, from 1 to 1800, plus either an audio url, parts or silence mode, and between 1 and 200 video slots. Each slot has a source_url that is a media.sume.com artifact, a start on the output timeline that is 0 for the first slot, and a duration of at least 0.2 seconds.
Transitions are optional on slots after the first: fade, wipeleft, wiperight, slideup, slidedown or dissolve, up to 1 second. Use a short fade or none; hard cuts suit Shorts pacing.
curl -sS -X POST https://api.sume.com/v1/timeline-1.0/plan \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"audio": {"mode": "silence", "duration_seconds": 24},
"video": [
{"source_url": "https://media.sume.com/artifacts/artf_demo/a.mp4", "start": 0, "duration": 8},
{"source_url": "https://media.sume.com/artifacts/artf_demo/b.mp4", "start": 8, "duration": 8},
{"source_url": "https://media.sume.com/artifacts/artf_demo/c.mp4", "start": 16, "duration": 8}
]
}'Plan first, then render
POST /v1/timeline-1.0/plan is unbilled. It checks the schema and the hosting of each URL, compiles the program and returns duration_seconds, segment_count, billable_minutes and estimated_cost_usd_micros. It does not create a job or reserve credits. Render with POST /v1/timeline-1.0/render using an Idempotency-Key, which is required. Default mode is async, so poll GET /v1/jobs/{id}/status, or pass mode sync to wait up to 30 seconds.
The reserve is based on audio.duration_seconds, so a declared 60 seconds reserves one minute. Declare the real length.
Tips for a tight Short
Keep an eye on the soft warnings in the result. Short sources are padded or looped, which is not a failure but can look wrong. If the source clip is shorter than the slot you declared, shorten the slot.
- Coverage can stop at most 0.5 seconds before the end of the audio spine.
- Use output fps 24, 25, 30 or 60, or omit it to match the sources.
- Stay under 61 seconds if you want to stay in one billable minute.
Limits of this advice
The YouTube page we read gave a recommendation, not a hard limit, and did not state aspect ratio or file size. Check Google's requirements for those. Our claims about Timeline come from the Sume docs page for Timeline 1.0.
A worked example
Say you want a 24-second Short built from three 8-second shots. You generate the three clips with POST /v1/videos, each at 8 seconds, which sits inside the 3 to 10 second range of sume/auto and inside every catalog model's range. Their artifacts live on media.sume.com. You declare audio.duration_seconds as 24, send the three slots with start values 0, 8 and 16, and call plan. The answer reports 1 billable minute, so the stitch itself is $0.10. The clip generation is billed separately at each model's price, and Timeline does not change it.
If you later extend the ad to 70 seconds for a different placement, the plan tells you at once that it is now 2 billable minutes. That is the reason to plan every length before you render.
Timeline does not generate anything. It needs finished artifacts, so the cost of a Short is the cost of the shots plus the stitch. If your shots come from a Format run, use the artifact URLs from the finished run. If they come from the video route, fetch the unsigned_urls from the poll. Either way, the slot needs a media.sume.com artifact, and an arbitrary external URL is rejected by plan before any render.
Sources
Related posts
More in Use cases
- AI album cover generator: square art at 3000×3000
Generate square album art, then upscale: Apple recommends at least 3000×3000. On Sume, generate 2400×2400 and upscale it 1.25× to reach 3000×3000.
- AI avatar for online course videos: build and update lessons
Use an AI avatar as your online course instructor: one reusable avatar, a short talking video per section, captions, and one Timeline join per lesson.
- Talking avatar for PowerPoint presentations, slide by slide
Make a talking avatar presenter for PowerPoint: one Sume clip per slide, up to 60 seconds each, in 16:9 or 4:3 to match the slide, inserted as MP4.
- AI avatar for YouTube videos: Shorts and long-form
Use an AI avatar in YouTube videos: a 9:16 talking video of up to 60 seconds for a Short, or 16:9 segments joined into one long-form video.
Written by Sume