Zoom video background: MP4 or MOV, 360p to 1080p, from Sume
Zoom accepts an MP4 or MOV video background between 480x360 and 1920x1080. Generate a 16:9 clip on Sume at 720p or 1080p and skip the 4K trap.

Zoom takes a video virtual background as an MP4 or MOV file with a resolution from 480x360 pixels (360p) up to 1920x1080 pixels (1080p). To make one on Sume, request a 16:9 clip at 720p or 1080p from a video model that lists those values in its catalog, and download the MP4. Stay off 4K: it is above Zoom's stated maximum.
This post lines up Zoom's published limits with what the Sume video API lets you ask for, so the first file you upload is already inside the range.
What does Zoom require for a video background?
Zoom's support article lists the video formats as MP4 or MOV and gives a resolution range with a minimum of 480x360 and a maximum of 1920x1080. For image backgrounds it lists 24-bit PNG or JPG/JPEG, a 15 MB maximum, a suggested minimum of 1280x720, and advice to crop to the aspect ratio of your camera. The article does not give a maximum video length or file size, so this post does not either.
| Item | Zoom's stated value |
|---|---|
| Video formats | MP4 or MOV |
| Video resolution | 480x360 minimum, 1920x1080 maximum |
| Image formats | 24-bit PNG or JPG/JPEG |
| Image size | 15 MB maximum |
| Image resolution | 1280x720 suggested minimum, match your camera's aspect ratio |
Which Sume resolution should you ask for?
The Sume video catalog reports each model's supported resolutions, aspect ratios and durations, and a value a model does not advertise returns a 400 instead of being dropped. Use that to your advantage: ask for 16:9 and 1080p, or 720p for a lighter file.
Gemini Omni Flash 1.1 (gemini-omni-flash-1.1) accepts 360p, 720p, 1080p and 4K in 16:9 or 9:16 for 3 to 10 seconds, with native audio. Seedance 2.0 lists 480p, 720p and 1080p with 16:9 among its ratios and 4 to 15 seconds. Either fits Zoom's range as long as you do not pick 4K.
| Model id | Resolutions | Duration | Fits Zoom's 1080p cap |
|---|---|---|---|
| seedance-2 | 480p, 720p, 1080p | 4 to 15 s | Yes, at any listed value |
| gemini-omni-flash-1.1 | 360p, 720p, 1080p, 4K | 3 to 10 s | Yes, except 4K |
How do you request the clip?
Submit to POST /v1/videos, poll the polling URL until the job is completed, then download the content URL as an MP4. The request below asks for a quiet office with slow drifting light and no people, which keeps the motion calm behind a speaker.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "seedance-2",
"prompt": "Empty bright studio office, slow drifting window light, no people, locked camera",
"aspect_ratio": "16:9",
"resolution": "1080p",
"duration": 10,
"generate_audio": false
}'What about a still background instead?
If a moving background is more than you need, request a 16:9 image from POST /v1/images and set output_format to png or jpeg, both of which Zoom lists. The image API accepts png, jpeg and webp, so choose one of the first two. Check the file against Zoom's 15 MB limit before uploading.
To confirm the dimensions of a finished clip, the video inspect API probes one clip your workspace already owns and returns probe facts, so you can compare them with the 1920x1080 maximum before you share the file around your team.
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