YouTube end screens need a 25-second video: plan the clip length
YouTube end screens need videos 25 seconds or longer. Most Sume video models stop at 15 seconds, so here is how to reach 25 with long models or Timeline.

YouTube's upload documentation says end screens need a video that is 25 seconds or longer. A single clip from most Sume video models will not reach that, so either choose a model with a 30-second ceiling or assemble several clips with Timeline.
What YouTube states
The YouTube upload page, read on 2026-10-03, lists the limits relevant to a batch.
| Item | Limit |
|---|---|
| Title | 100 characters |
| Description | 5,000 characters |
| Videos per upload batch | Up to 15 at a time |
| End screens | Video must be 25 seconds or longer |
Which Sume models reach 25 seconds
The video docs state per-model duration ranges. seedance-2.5 accepts 4 to 30 seconds, wan-3.0 accepts 2 to 30 seconds, higgsfield-genjutsu (Motion Transfer) accepts 4 to 30 seconds when its provider is configured, and h3-max-recast accepts 5 to 30 seconds. The docs add that every other catalog model tops out at 15 seconds.
That means a single generated clip can cover an end-screen video only on those models. Read supported_durations from GET /v1/videos/models for the live list, since limits are not uniform.
Assembling 25 seconds from shorter clips
Timeline 1.0 takes one audio spine and ordered video[] slots and returns one MP4. It accepts audio.mode: "silence" with a declared duration_seconds when there is no voiceover, and POST /v1/timeline-1.0/plan is an unbilled preflight that returns duration_seconds without creating a job. Two 13-second slots make a 26-second video, which clears the 25-second line with a second to spare.
curl -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": 26 },
"video": [
{ "source_url": "https://media.sume.com/artifacts/artf_demo/a.mp4", "start": 0, "duration": 13 },
{ "source_url": "https://media.sume.com/artifacts/artf_demo/b.mp4", "start": 13, "duration": 13 }
]
}'Practical notes
Timeline declares that coverage may trail the spine by at most 0.5 seconds, so leave margin above 25 and do not plan a 25.0-second render. Source URLs must already be this workspace's media.sume.com artifacts, so import external files first. A silent video is still valid for an end-screen carrier, but if you want a voiceover, pass audio.url instead.
Check the clip's real length from the job result before you upload.
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