Keep a sub-3-minute video out of YouTube Shorts: render it 16:9
YouTube treats square or vertical videos up to 3 minutes as Shorts. To keep a short clip as regular video, make it 16:9 on Sume with 1920 by 1080 Timeline.

YouTube's Shorts help page says square or vertical videos up to 3 minutes are Shorts, and that to keep a video long-form you should use a wider aspect ratio such as 16:9 (read 2026-10-04). If your 90-second tutorial must land as a regular upload, the ratio is the lever.
Sume's Timeline defaults to 1080 by 1920, which is vertical, so a default render of any length up to 3 minutes can be classified as a Short. Override it.
Set width and height
Timeline 1.0 accepts output.width and output.height as even integers from 256 to 2160. 1920 is below 2160 on the long side, so 1920 by 1080 works. Use the plan endpoint first; it compiles the program and returns an estimated cost without creating a job.
import os
import requests
body = {
"audio": {"mode": "silence", "duration_seconds": 90},
"video": [{
"source_url": os.environ["CLIP_URL"],
"start": 0,
"duration": 90,
"fit": "cover",
}],
"output": {"width": 1920, "height": 1080},
}
r = requests.post(
"https://api.sume.com/v1/timeline-1.0/plan",
headers={"Authorization": f"Bearer {os.environ['SUME_API_KEY']}"},
json=body,
)
print(r.status_code, r.json())If the source is vertical
A 9:16 source in a 16:9 frame needs a fit rule. cover crops, contain letterboxes, blur fills the sides with a blurred copy and stretch distorts. A render at $0.10 per output minute rounds up, so 90 seconds is 2 minutes, or $0.20.
If the AI clip itself should be wide, generate it 16:9. kling-3, seedance-2 and wan-3.0 all list 16:9. Shorts rules change, so reread the help page before a launch.
Sources
Related posts
More in Media tools
- Kids video background music: a Lyria prompt that stays instrumental
A copy-ready music prompt for a children's video bed: seven brief axes, a 'no vocals' ending, and one $0.125 Sume generation, with length set in the prompt.
- Korean sale captions: slam and punch reject Hangul, use black-outline
Sume video-captions refuses Hangul text on slam, punch and tiktok-green with caption_hangul_text_latin_style. Pick black-outline or korean-ad; $0.20 per job.
- LinkedIn video thumbnail under 2 MB: pull the frame with Sume
LinkedIn video ad thumbnails are JPG or PNG up to 2 MB. Pull a still from your clip with Sume's video frames endpoint and check its size before upload.
- Lip-sync a 20-second line: H3 Max takes 14.8 s of audio, so split it
MiniMax H3 Max lip sync on Sume accepts 5 to 14.8 seconds of audio. How to cut a 20-second line into two takes, or use Fabric for a longer face-to-camera line.
Written by Sume