Shorts ad CTA shows at 3 or 10 seconds: where the hook goes
Google says the Shorts ad CTA appears 3 seconds in for PMax, App and Demand Gen, and at 10 seconds for Video View and Reach. Put the hook before it with Sume.

Google Ads Help says the call-to-action button appears 3 seconds into a Shorts ad for Performance Max, App and Demand Gen campaigns, and 10 seconds in for Video View and Reach campaigns (read 2026-10-03). Your hook and offer should be on screen before that moment, because that is when the viewer is offered the click.
Sume can burn the hook text into an existing clip and can pull stills at 0, 3 and 10 seconds to check it.
What does Google's page specify?
The same help page has the asset rules. The ones that shape a hook are the first-60-seconds rule and the sound guidance.
- Google's 20% figure is its own claim.
- Recommended length is under 60 seconds.
- Shorts ads use the advertiser's channel name and description.
| Item | Google says |
|---|---|
| Upload | Video must be uploaded to YouTube |
| Length | Up to 3 minutes; only the first 60 seconds play on the Shorts feed |
| Orientation | 9:16 vertical recommended; horizontal serves with blurred top and bottom |
| CTA timing | 3 seconds (Performance Max, App, Demand Gen) or 10 seconds (Video View, Reach) |
| Sound | Sound-on assets recommended; Google says sound increases conversions by over 20% |
| Action ads | 10-30 second videos suggested for action-oriented ads |
How do I burn the hook in before the CTA?
POST /v1/video-captions takes a public HTTPS video URL and cues, each with text, start and end. Authored cues skip speech-to-text, so a silent clip works. Each standalone caption job is $0.20 for videos up to 60 seconds.
Put the offer in a cue that ends before the CTA time: start 0 and end 2.5 for the 3-second case.
curl -sS -X POST https://api.sume.com/v1/video-captions \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"video_url":"https://example.com/short.mp4",
"style":"slam",
"cues":[{"text":"Free shipping ends Sunday","start":0,"end":2.5}]}'How do I check the frames?
POST /v1/video-inspect reads one clip on media.sume.com and returns stills at the timestamps you give, with frames: {"at": [0, 3, 10]}. Look at the 3-second and 10-second stills to confirm the hook is on screen and nothing important sits where the CTA card will cover it.
Import the clip with POST /v1/media-imports first if it is not already hosted there; inspect does not fetch arbitrary URLs.
curl -sS -X POST https://api.sume.com/v1/video-inspect \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{"video_url":"https://media.sume.com/artifacts/artf_demo/short.mp4",
"frames":{"at":[0,3,10]}}'What Sume does not do
Sume cannot tell you where Google draws the CTA card on a given device, set CTA timing, or upload to YouTube. Upload and campaign type are your steps in Google Ads.
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