Avatar over a product demo in one vertical ad: compose costs $0.02
Stack a Sume Avatar 1.0 clip above a product demo in one 9:16 ad with Timeline compose for a flat $0.02. How to set it up and what to check.
To put an avatar above a product demo in one vertical ad, render the avatar clip, then use Sume's Timeline compose to stack the two. Compose costs a flat $0.02 per render (read 2026-10-06), which is small next to the avatar clip itself.
Compose supports stack and overlay layouts. Stack places one video above the other. Overlay places one on top, which suits a small presenter in a corner.
Setup
Both inputs must be media.sume.com URLs, so import any outside file first. Choose the layout, then choose how each video fits its box, using cover to fill or contain to show the whole frame. The linked post covers the fit choice for a 16:9 source in a vertical stack.
| Layout | Use for | Price |
|---|---|---|
| stack | Avatar on top, demo underneath | $0.02 flat |
| overlay | Small presenter over full-frame demo | $0.02 flat |
What to watch
The output duration is clamped to the shorter source, so a 20-second avatar over a 15-second demo ends at 15. Match the lengths first. If the demo has no audio, compose warns that the video has no audio.
Decide which video carries the sound. The avatar's voice is usually the one to keep.
A 9:16 example
For a vertical ad, make the avatar clip in 9:16 or 1:1, import the demo recording, and stack them with the avatar on top. Pick cover for the avatar so it fills its box, and contain for the demo so no part of the screen is cut off.
Total finishing cost for the stack is $0.02. If you add captions on the stacked result, that is a separate $0.20 pass, and if you add a soundtrack through the timeline, it is $0.10 per started minute.
Before you render
Look at the safe areas of the platform you are posting to. Interface buttons often cover the lower part of a vertical frame, so keep the demo's important content out of the bottom band, and keep the avatar's face away from the top edge.
Check lengths and audio first. Compose does not extend a short clip, so trim or extend sources before you stack them. The same price applies if you run it twice, so a test render costs $0.02.
Tradeoffs
Stacking two 720p sources into one vertical frame gives each a smaller area, so text inside the demo may be hard to read. Use overlay with a larger demo if the screen text matters.
Sources
Related posts
More in Media tools
- Sume video trim output: libx264, yuv420p, AAC, exact vs keyframe
Exact trim re-encodes with libx264 and yuv420p, audio as AAC; keyframe copies the stream. Neither YouTube's Shorts nor TikTok's ad page names a codec.
- Timeline slots must reach within 0.5 s of the voiceover: 24 s example
Lay out Sume Timeline 1.0 for a 24-second voiceover: four 6-second slots from 0, last within 0.5 s of the end. Plan it free, render for $0.10.
- Sume timeline with silent audio: audio.mode silence and its limits
Set audio.mode to silence in Sume Timeline 1.0 for a declared length with no spine file. Do not send url, parts, gain_db or source_in, and no ducking bed.
- Compose stacks a still over a video for up to 300 seconds, flat $0.02
A 3-minute Short with a headline image on top fits Sume timeline compose's 300-second ceiling at a flat $0.02. How the stack is sized and what clamps.
Written by Sume