A CTA plate over the last clip of a 60-second Short: $7.72 all in
Six 10 s Omni Flash clips ($7.50 at 720p), one Nano Banana 2.1 plate ($0.10), a $0.02 compose overlay and a $0.10 Timeline render make a 60 s Short for $7.72.
To put a call-to-action card over the last clip of a vertical Short, make the card as a still and use Timeline compose with operation overlay: it is $0.02 per job. With six 10-second Omni Flash 1.1 clips at 720p ($7.50), a 1K Nano Banana 2.1 plate ($0.10) and the $0.10 Timeline render, the 60-second Short is $7.72.
Shorts are vertical and run up to 3 minutes (YouTube Help, read 2026-10-09). Compose's default output is 1080x1920, which is that shape.
Cost line by line
| Item | Unit price | Qty | Cost |
|---|---|---|---|
| Omni Flash 1.1 720p, 10 s, 9:16 | $1.25 | 6 | $7.50 |
| Nano Banana 2.1 plate, 1K | $0.10 | 1 | $0.10 |
| Timeline compose (overlay) | $0.02 flat | 1 | $0.02 |
| Timeline render, 1 minute | $0.10 | 1 | $0.10 |
| Total | $7.72 |
Overlay the plate
Both inputs must be this workspace's media.sume.com artifacts; import them first. The still stays on screen for the whole video layer, and the output length comes from the video. So compose the sixth clip only, then put its MP4 in the last Timeline slot. Overlay layout keys are position, width_ratio (0.05 to 1, default 0.9), margin_ratio (0 to 0.45) and video_fit.
curl -X POST https://api.sume.com/v1/timeline-1.0/compose \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: cta-plate-001" \
-d '{"operation":"overlay",
"image":{"url":"https://media.sume.com/artifacts/artf_demo/cta.png"},
"video":{"url":"https://media.sume.com/artifacts/artf_demo/clip6.mp4"},
"layout":{"position":"bottom","width_ratio":0.9,"margin_ratio":0.08},
"output":{"width":1080,"height":1920}}'What to check
- Do not mix stack keys (split, ratio) with overlay keys; the request returns 400.
- The plate covers part of the frame for the whole clip. If the plate should appear only for the last 3 seconds, trim clip 6 into two pieces and compose only the second.
- Compose works on one still and one video, so a plate over several clips means one compose job per clip, $0.02 each.
- A silent source video gives a compose_video_has_no_audio warning, not a failure.
Sources
Related posts
More in Use cases
- Cut away to B-roll without breaking the voice: one detached spine
Detach the A-roll audio once ($0.01) and render three slots in one Timeline job ($0.10): 32 s of picture, B-roll over the middle, the voice unbroken.
- Daily horoscope Shorts for 12 signs: a card and a voice for $2.66
Twelve horoscope Shorts, each a 1K card, 450 characters of TTS and a one-minute Timeline render, cost $2.66 per day on Sume ($0.2214 each).
- Daily news brief voiceover: 1,400 characters a day for 30 days
A 1,400-character daily brief costs $0.0665 on Sume TTS, so 30 days is $1.995. Table for 1,000, 1,400 and 2,000 characters, plus a retry-safe daily job.
- Do 480p AI video clips pass TikTok's ad minimums? 540x960 and 640x640
TikTok's non-Spark ad minimums are 540x960, 960x540 and 640x640. A 480p AI clip is named for 480 pixels on its short side, which is below all three. Use 720p.
Written by Sume