DJ set teaser: flyer above the booth clip, lineup as captions
Stack a night's flyer over 15 seconds of booth footage with timeline compose ($0.02), then burn set times as cues ($0.20). The clip's own audio stays.
To make a DJ set teaser, trim 10 to 15 seconds from a phone clip of the booth, then use timeline compose with the stack operation to put the night's flyer in the top region and the clip underneath (a 40/60 split of a vertical frame), and finally burn the set times as caption cues. Compose is $0.02 flat, trim is $0.02, and captions are $0.20 for a clip up to 60 seconds, so $0.24 in total. The audio you recorded in the room is kept.
Why stack the flyer instead of overlaying it?
Timeline compose has two operations. Overlay floats a plate over the video. Stack tiles two regions of one frame, with the still on top by default and a ratio between 0.1 and 0.9 for the still's share. A flyer is information you want readable the whole time, and a strobe-lit booth clip behind it would fight the text. Stacking keeps both clean: flyer on top, motion below.
The output length always comes from the video layer. The still stays up for the whole clip and cannot make the clip longer, and the ceiling is 300 seconds. Pick a short loop-friendly stretch, such as the drop.
What does the compose request look like?
The field that picks stack or overlay is operation, not mode (mode is the usual async or sync choice). Both URLs must already be media.sume.com files in your workspace, the image must probe as a still and the video as a video. An Idempotency-Key header is required.
{
"operation": "stack",
"image": { "url": "https://media.sume.com/artifacts/artf_demo/flyer.png" },
"video": {
"url": "https://media.sume.com/artifacts/artf_demo/booth-clip.mp4",
"source_in": 0,
"duration": 15
},
"layout": { "split": "horizontal", "image_region": "top", "ratio": 0.4 },
"output": { "width": 720, "height": 1280, "fps": 30 }
}What does it cost and what about the sound?
Compose uses the audio of the video layer. If the clip is mute you get a warning, not a failure. Whether you may post a venue recording is a rights question for you and the venue; Sume only cuts and composites the file you provide.
| Step | Route | Rate |
|---|---|---|
| Cut 15 s from the phone clip | POST /v1/video-trim | $0.02 |
| Flyer above clip | POST /v1/timeline-1.0/compose | $0.02 flat |
| Set times as cues | POST /v1/video-captions | $0.20 (clips up to 60 s) |
| Total | $0.24 |
How should the lineup cues read?
Keep each cue under about six words: a name and a time, such as Doors 9 PM or Main set 11 PM. Cues carry text, start and end in seconds and skip speech-to-text, so a loud room causes no transcription errors. Burn captions after compose, because they sit on the final frame, and choose a caption placement that avoids the seam where the flyer meets the clip using the anchor_ratio design override.
Sources
Related posts
More in Use cases
- Double-exposure portrait from two photos with Nano Banana 2.1
Blend a portrait and a landscape into one double exposure: two input_references, a pinned 4:5 ratio, Nano Banana 2.1 at 1K, and the 10-reference cap on Sume.
- eBay listing video: no URLs or calls to action, check before upload
eBay's images, videos and text policy bars contact details, links and calls to action in listing video. Check stills and speech on Sume before you upload.
- Game devlog video with no voice-over: captures, a bed, cue cards
Build a 45-second devlog from gameplay captures: trim each clip, render on a silent spine with a music bed, then burn feature names as cues. $0.525.
- Game patch notes video: dim the capture, one caption card per change
A patch notes video is gameplay dimmed 50 percent, then one caption card per change. Dim is $0.02 with a free check; the cards are $0.20 for up to 60 s.
Written by Sume