Cyber Monday ad in 9:16, 1:1 and 16:9 from one clip with Timeline
Resize one offer video to vertical, square and landscape with Timeline 1.0 output width and height, fit blur or cover, for $0.30 across three renders.

To reuse one Cyber Monday offer video in vertical, square and landscape, render it three times through Timeline 1.0 with a different output.width and output.height each time. Set the clip's fit to blur to keep the whole frame on a blurred fill, or leave the default cover to crop to fill. Each render is $0.10 for a clip up to a minute, so three sizes cost $0.30. Cyber Monday is 30 November 2026, three days after Black Friday.
The three bodies
Everything but the output size stays the same. The clip is uploaded (or generated) once and referenced by its media.sume.com URL. The audio spine is the clip's own sound: detach it once with POST /v1/audio-detach ($0.01, wav by default) and use that file as audio.url, with audio.duration_seconds set to the clip length.
| Placement | width | height |
|---|---|---|
| Vertical 9:16 | 1080 | 1920 |
| Square 1:1 | 1080 | 1080 |
| Landscape 16:9 | 1920 | 1080 |
Request template
{
"audio": {
"url": "https://media.sume.com/artifacts/artf_demo/offer.wav",
"duration_seconds": 15
},
"video": [{
"source_url": "https://media.sume.com/artifacts/artf_demo/offer.mp4",
"start": 0,
"duration": 15,
"fit": "blur"
}],
"output": { "width": 1080, "height": 1080 }
}Which fit to choose
| fit | Effect | Use when |
|---|---|---|
| cover (default) | Fills the frame and crops the overflow | The subject sits in the middle |
| contain | Whole frame, empty bars | You need the exact frame, bars are fine |
| blur | Whole frame on a blurred fill | Text near the edges must survive |
| stretch | Distorts to fill | Almost never |
Check text before you ship
Offer text burned into a 9:16 clip lives near the bottom, which cover into 16:9 will cut off. Preview the opening and a text-heavy frame with POST /v1/video-frames (unbilled), then choose blur. Do the sizing before captions: burn captions onto each finished size so the phrase placement matches that frame.
Limits
Timeline can re-frame but it cannot re-compose: it will not move a subject or generate new background beyond the blurred fill. If a landscape version needs real extra scene, generate it with a video model at 16:9. An output frame rate is inherited from the sources unless you set output.fps, and a rate that differs is met by repeating or dropping frames, which can judder motion. Run the unbilled plan call first to see the rounded-up billable minutes.
Sources
Related posts
More in Media tools
- Edit Video in Sume: which models appear and why H3 Max does not
Sume's Edit Video mode lists Auto, Kling 3.0, Wan 3.0 and MiniMax H3 and needs a reference video. H3 Max and Grok Imagine are missing; the API differs.
- ElevenLabs sound effects API: 0.5-30 s, loop, and Sume's route
ElevenLabs POST /v1/sound-generation takes duration_seconds 0.5-30 and a loop flag. Sume lists no sound-effect endpoint; here is the music route and its limits.
- English to Korean captions: style follows the text, not language
Localising a video to Korean? Sume's caption style follows the wording, and a Latin style on Hangul text is a 400. Pick styles per locale before a batch.
- Extract audio from an AI avatar video as a WAV with one API call
Sume audio detach pulls the track of one hosted video into a WAV or MP3 for $0.01. The request, the 16 kHz mono option, the caps and the no-audio error.
Written by Sume