Black Friday countdown video ad: burn the days-left text
Meta says countdown overlays create Black Friday urgency. A countdown is authored text, so burn a new days-left cue onto one clip each day with Sume.

A Black Friday countdown video needs text that changes every day, not speech, so treat it as authored overlay copy. Keep one clean clip, then send it to Sume's POST /v1/video-captions with cues such as "3 days left" at set times; the docs say this path "burns exactly that copy at those times" and skips speech-to-text.
Meta's holiday guide (published 2026-08-11, read 2026-09-30) says the deal phase uses Stories with countdown timers and CTAs, and that "Countdown overlays create Black Friday urgency". Sume facts are from Video captions and Timeline 1.0. This burns text into the file; it is not Meta's own countdown sticker.
Why not use speech captions?
Speech captions need audible speech. A silent clip fails as caption_no_speech with next_action: use_overlay_captions. Authored cues (or segments) with text, start and end avoid that, and they are mutually exclusive with words and script_text. For styling options, see customize burned-in captions.
How do I make one cue set per day?
Loop over the days left and call the caption endpoint on the same clean source each time. Each call is one job with its own Idempotency-Key, and the source is never regenerated.
const clean = "https://media.sume.com/artifacts/example/clean.mp4";
for (const daysLeft of [3, 2, 1]) {
const res = await fetch("https://api.sume.com/v1/video-captions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.SUME_API_KEY,
"Content-Type": "application/json",
"Idempotency-Key": "bf-countdown-" + daysLeft,
},
body: JSON.stringify({
video_url: clean,
style: "punch",
cues: [{ text: daysLeft + " days left", start: 0, end: 4 }],
}),
});
console.log(daysLeft, res.status);
}What does each version cost and how long can it be?
| Item | Value |
|---|---|
| Standalone caption job | $0.20 USD for videos up to 60 seconds (fixed estimate; confirm in GET /v1/catalog) |
Cue start / end | 0 to 60 seconds in the OpenAPI schema |
| Cues per request | 1 to 200 |
| Cue text | Up to 400 characters, a newline allowed for a two-line card |
| Timeline default output | 1080x1920 MP4, vertical |
Where does the clean clip come from?
Anywhere that ends as a Sume-hosted media.sume.com file: a Format run, a video job, or a Timeline render. Make the vertical cut once, then caption it per day. The four-phase plan this belongs to is in holiday ad creative by phase.
Sources
Related posts
- How to burn captions onto a video with the Sume API
- Customize captions API: color, position, size, and words per line
- Holiday ad creative by phase: four videos, one bulk run
- Facebook Feed video captions: burn them onto a clip with no speech
- Cut one product video into feed cutdowns with the video-trim API
More in Use cases
- Bluesky video captions: WebVTT sidecar vs burned-in
Bluesky video embeds take WebVTT caption files next to the video. Sume burns captions into pixels, so build the VTT yourself from sentence segments.
- Break down a UGC ad by scene: $0.30 analysis or free stills?
To study a UGC-style ad, video inspect gives free stills and a $0.01 per minute transcript; the legacy analysis adds typed scenes for $0.30. What each returns.
- Virtual staging disclosure: California AB 723 and originals
California AB 723 asks listings with digitally altered photos to say so and link to the unaltered originals. How to keep original and edit as two URLs.
- California AI Transparency Act date, and latent vs manifest marks
AB 853 delays the California AI Transparency Act to August 2, 2026. What latent and manifest mean in the bill, and what Sume's docs say it ships.
Written by Sume