Q4 gift guide video: five picks, five stills, price cues
Build a five-pick holiday gift guide video on Sume: five stills, 400 characters of TTS, a Timeline render and one cue caption job for prices. Read 2026-10-10.

A five-pick gift guide video costs about $0.82 on Sume: five Nano Banana 2.1 stills ($0.50), 400 characters of TTS ($0.0190), one Timeline render ($0.10) and one caption job with price cues ($0.20). The prices on screen are cue text, so they can never be misdrawn.
A gift guide is a list, and lists fit Timeline slots. Each pick gets one still and a sentence of voice-over; the price is a timed cue. If a price changes before Christmas, you recaption instead of regenerating. Rates are from the Sume pricing code (read 2026-10-10).
What is the endpoint chain?
Think of the guide as five rows in a table and make one job per row.
POST /v1/imagesx5 withgoogle/nano-banana-2.1, 1K, 9:16, one product mood each; use references for real products.POST /v1/tts-1.0/generatewith an intro and five lines,segmentation.mode: "sentence", so you get six start times.POST /v1/timeline-1.0/renderwith six slots: the intro still and five picks, starts from the segment times.POST /v1/video-captionswithcues: five entries like 'Reading lamp, $38' each timed to its slot.
What does it cost?
The video scales by number of picks only on image and voice, since the render and captions are flat.
| Picks | Stills | Voice (80 chars each) | Total with render and captions |
|---|---|---|---|
| 3 | $0.30 | $0.0114 | $0.611 |
| 5 | $0.50 | $0.0190 | $0.819 |
| 8 | $0.80 | $0.0304 | $1.130 |
What are the limits?
Timeline renders up to 200 slots, and renders over 12 segments are chunked automatically, so an eight-pick guide is fine. The render is billed per started output minute, so keep the guide under 60 seconds to pay one unit of $0.10.
Image models draw plausible products, not your SKU. If the exact product matters, upload a real photo as a reference and check GET /v1/images/models for the count it takes. Do not claim a model drew your real item. Disclose affiliate links in the post itself; Sume does not add that for you.
For the Q4 volume, a bulk queue helps; see the 12-days-of-deals queue. The caption cues shape is on the Video captions page.
How do I vary it for another audience?
Change only the TTS text and the cues. The same five stills with a different voice line is one TTS job ($0.019 for 400 characters), one render ($0.10) and one caption job ($0.20), or $0.319 per variant. That is the cheapest way to test two angles on the same list; compare with a three-hook A/B test from one body.
Pre-publish checklist
Cross-check each price cue against the product page on the day you post. Cues are plain text, so the fix is a recaption at $0.20, not a new render.
Keep the guide short enough that the last pick still gets attention. Five picks at six seconds each is a 30-second video.
- Confirm each slot start matches its voice line.
- Check the still for each pick looks like a gift, not an ad.
- Keep shipping cutoff dates in the post, not the video.
Sources
Related posts
More in Use cases
- Q4 holiday campaign budget: 34 posts priced from Sume endpoint rates
Price a Q4 holiday campaign on Sume: 28 daily stills with voice, 4 weekly 720p clips and 2 gift guides. Endpoints and totals, read 2026-10-10.
- Record store Black Friday drop: original music bed, no sound-alikes
A record store can make four original instrumental beds for $0.50 with the Sume Music Router. Why prompts should never name artists, and how to set length.
- Daily special video for 21 cents: TTS, one still, one render
A restaurant daily special as a 12-second video on Sume: one still, 180 characters of TTS and a Timeline render. Cost per day and per month, read 2026-10-10.
- Detach 13 seconds of speech from a clip and lip-sync it on H3 Max
Sume can detach audio from a hosted clip by time range, then drive a talking face with H3 Max lip-sync. $1.31 for 13 seconds; rights and limits explained.
Written by Sume