Prime Big Deal Days: three deal drops a day, one clip, new price text
Amazon drops new Prime Big Deal Days deals at midnight, 8 a.m. and 1 p.m. PDT. Swap price text per drop with authored caption cues, no clip re-render.

Amazon says Prime Big Deal Days run October 6 and 7, starting at 12:01 a.m. PDT, with new deals dropping three times a day: midnight, 8 a.m. and 1 p.m. PDT. If your offer changes by drop, your clip's price text changes by drop. You can handle that with one rendered product clip and several caption jobs that burn different text onto it, using the authored cues field of the Sume video captions endpoint.
Why captions, not a new render
The video captions endpoint accepts cues with text, start and end, and when you pass authored cues it skips speech-to-text. That matters for a silent product clip: with no cues, a silent video fails with the caption_no_speech code. With cues, the same silent clip gets overlay copy.
The clean master stays untouched, and each variant is a new job against it. Every accepted standalone caption job is $0.20 for videos up to 60 seconds under the docs' current fixed estimate, so three drops times four products is twelve jobs, or $2.40 at that rate.
| Drop (PDT) | Amazon timing | Clip work |
|---|---|---|
| Midnight | New deals, Oct 6 and 7 | Variant A: opening price text |
| 8 a.m. | New deals | Variant B: swapped price or badge |
| 1 p.m. | New deals | Variant C: last-chance text |
A caption job per drop
The sample below sends one job. Run it once per variant with a different text value and a different idempotency key, and keep the returned job ids so you can poll each one.
import json, os, urllib.request
def main():
key = os.environ["SUME_API_KEY"]
body = {
"video_url": "https://media.sume.com/artifacts/example/clean.mp4",
"style": "punch",
"cues": [{"text": "Deal drop 2: 25% off today", "start": 0.5, "end": 4.0}],
}
req = urllib.request.Request(
"https://api.sume.com/v1/video-captions",
data=json.dumps(body).encode(),
headers={
"Authorization": f"Bearer {key}",
"Content-Type": "application/json",
"Idempotency-Key": "pbdd-drop-2-sku-101",
},
)
with urllib.request.urlopen(req) as resp:
print(resp.status, resp.read().decode())
main()
Limits
The video must already be a public URL the endpoint can read. Burned-in text cannot be edited afterwards, so keep the clean master. Marketplace rules decide whether price text in a video is allowed on a given placement, and Amazon's page does not say, so check your ad type's creative policy first. A 25% figure in the sample is a placeholder, not a recommendation.
Sources
Related posts
More in Use cases
- Amazon's Prime Day video advice: product in 2 seconds, sound off
Amazon Ads' Prime Day guide says show the product in the first two seconds and design for sound-off. How to add captions and test the opening with Sume.
- Amazon product tags on Shorts: no timestamps, so cut the product beat
Amazon products can be tagged in YouTube Shorts, but product timestamps are not available on Shorts. Build a clear product beat with Sume trim and Timeline.
- Amazon shoppable video: 1 to 12 minutes, 5 GB, MOV or MP4
Amazon's shoppable video takes MOV or MP4, up to 1080p, 5 GB, 1 to 12 minutes, 4 per product. One AI clip is too short, so assemble the cut on Sume.
- Amazon Sponsored Brands video: no letterboxing, lower right clear
Amazon's Sponsored Brands video spec says avoid letterboxing and keep text out of the lower right. Test both on a still pulled with Sume video frames.
Written by Sume