Timeline renders 1080x1920 by default: set size for square or 16:9
Sume Timeline 1.0 outputs 1080 by 1920 MP4 unless you set output.width and height, even integers 256 to 2160. Sizes for 1:1, 4:5 and 16:9 shown.

You joined clips on Sume and the result is tall and narrow. That is the default: Timeline 1.0 outputs a 1080 by 1920 MP4 unless you say otherwise, which is 9:16 and suits Reels, Shorts and TikTok.
To change it, set output.width and output.height. Both must be even integers from 256 to 2160. video[].fit decides how a source fills the frame: cover (default), contain, stretch or blur.
Sizes that fit the limits
All four sizes use even numbers within range. A 4K width of 3840 does not fit, since the cap is 2160.
| Shape | Width | Height | Use |
|---|---|---|---|
| 9:16 | 1080 | 1920 | Default; Reels, Shorts, TikTok |
| 1:1 | 1080 | 1080 | Square feed video |
| 4:5 | 1080 | 1350 | Portrait feed video |
| 16:9 | 1920 | 1080 | Landscape, regular YouTube video |
Set it in the request
import json
import os
sizes = {"square": (1080, 1080), "wide": (1920, 1080), "tall": (1080, 1920)}
w, h = sizes[os.environ.get("SHAPE", "square")]
body = {
"audio": {"mode": "silence", "duration_seconds": 10},
"video": [{"source_url": "https://media.sume.com/artifacts/artf_demo/a.mp4", "start": 0, "duration": 10, "fit": "blur"}],
"output": {"width": w, "height": h},
}
print(json.dumps(body, indent=2))Post the body to /v1/timeline-1.0/render with an Idempotency-Key. The rate is $0.10 per output minute, rounded up, whatever the size.
Sources
Related posts
More in Media tools
- Transparent-background product cutouts with GPT Image 2.5
Make a PNG product cutout with a transparent background through Sume's Image API, then place it on each marketplace's own background. Request fields and checks.
- Transparent PNG: generate it or cut it out?
Sume lists a background option on ChatGPT Image 2.5: auto, transparent or opaque. Generate a transparent PNG directly, or cut out an existing image.
- Trim a supplier product video to 30 seconds with Sume, $0.02
Channels cap video length differently. Cut one clip to the range you need with Sume's video-trim endpoint, $0.02 per job, frame-accurate by default.
- Trim the silent lead-in: first spoken word from STT, then video trim
A clip that starts with two seconds of nothing loses viewers. Read the first word's start time from STT, then cut with video trim, exact or keyframe.
Written by Sume