Blog

Use cases

Worked examples on Sume's catalog Formats and endpoints: product video and photography, try-on, app and product ads, logo animation, and more.

Start with: Ready-made Formats for product video: the Sume Format catalog

Sponsored Snaps headline: 24 to 28 characters, check a batch

Snapchat's Sponsored Snaps page recommends a 24-28 character headline on a 9:16 asset. Check a batch of headlines in Python before you queue the Sume clips.

Edit a 20-second AI video: Luma, Aleph 2 or Omni's 10-second input?

Omni edits clips of 10 seconds or less; Runway Aleph 2.0 edits 2 to 30 seconds; Luma lists video-to-video at 10, 15 or 20. Editing longer clips on Sume.

Google Play preview video: check the YouTube URL in Python

Google Play wants a plain YouTube URL: public or unlisted, embeddable, ads off, no timecode. A short Python check, plus how to make the MP4 with Sume first.

Meta image animation or your own image-to-video: which to run

Meta Advantage+ can animate a product image; you can animate it yourself on Sume. Compare control, and note Meta's differing label statements on third-party AI.

TikTok Shop: labeling real footage as AI is itself a violation

TikTok Shop's page counts labeling non-AI content as AI-generated as a false disclosure. How to keep a clearly camera-shot cut apart from a generated one.

Shopify Shop app Deals feed: what product clip to upload

Shopify's Winter '26 Edition adds shoppable video and a Deals feed to Shop. Brief one short usage clip per product with the Sume product-usage-demo Format.

3-minute Shorts and monetization: plan the cut and the price

YouTube ties Short monetization to the Shorts Feed and blocks claimed Shorts over a minute. Cut a 3-minute Short for $0.02 to $0.30.

TikTok Spark Ads have no duration limit: what file to post

TikTok's ad specs list mp4 or mov and no duration limit for Spark Ads, with captions taken from the organic post. Cut the post, not the ad.

Mac and Apple TV app preview: 1920x1080 landscape, probe it first

Apple lists 1920x1080 landscape for Mac and Apple TV previews, 15 to 30 seconds. Probe your clip with Sume video inspect before App Store Connect.

YouTube clip compilations: the reused content rule and narrative

YouTube's reused content policy flags clips edited with little narrative and allows storyline plus commentary. Add your text with caption cues.

Alexa shows 365 days of price history: keep deal clips honest

Amazon says Alexa for Shopping shows price history up to 365 days, so price claims are easy to check. Keep prices out of the frames and list claims for review.

TikTok Symphony avatars skip shoes and hats: what to do instead

TikTok's Symphony avatar help page lists shoes, hats and sunglasses as unsupported product avatars. See the page's rules, then test an alternative on Sume.

Event recap videos: one bulk queue, one run per session

Queue one recap per conference session with POST bulk-runs: concurrency window, per-item caps, how to read the queue, and why completed does not mean success.

App demo video through the sume-mobile-app-ugc Format: what to send

Call a catalog Format at the sume handle for an app demo video. Read its io profile first, send screens and copy, cap the spend, and test the receipt.

Restaurant promo video for TikTok Ads: check size before upload

A restaurant promo made with a Sume Format can fail TikTok's non-Spark minimums. Read width, height and size_bytes from the run receipt before you upload.

Product launch teaser: one Format call with a $25 spend cap

How to produce a launch teaser through the Sume Format API: the call, the per-run cap, the idempotency key, and what the receipt shows when it finishes.

Seasonal sale video: re-skin your own footage with sume-restyle

Reuse one product clip for a holiday sale by calling sume-restyle, which keeps motion, timing and cuts and rewrites the look. Inputs, limits and checks.

Podcast trailer: redo one part with previous_run_id, not a full rerun

Fix one weak scene in a podcast trailer by continuing the Format run with previous_run_id, so the agent keeps the rest. Rules, refusals and cost.

Real estate walkthrough video from listing photos: the 30-image limit

A Sume Format run accepts up to 30 images as attachments. How to send listing photos, keep room order, set a cap and read the walkthrough back.

Make a three-minute YouTube Short with a Format and check duration_ms

YouTube counts square or vertical uploads up to three minutes as Shorts. Call a Sume Format, then test duration_ms and aspect ratio on the receipt first.

X video ads loop under 60 seconds: design the last frame of a 45 s ad

X loops video ads shorter than 60 seconds and plays longer ones once. Plan the first and last second differently for each, then check them with Sume.

12 product clips with 12 voice lines: one join, one render, 15 cents

Twelve 75-character lines are 900 characters of TTS ($0.04275), one $0.01 audio join and a $0.10 render: $0.15275 for a 60-second product reel.

15 thumbnail tests (5 videos x 3 variants): $2.25 at 2K on Sume

Three 16:9 thumbnail variants for each of five videos is 15 images: $1.50 at 1K, $2.25 at 2K or $3.00 at 4K on Nano Banana 2.1 via Sume. YouTube's size rules.

X standalone video lists 16:9 and 1:1: set the Sume render size

Sume timeline renders 1080x1920 by default, but X's standalone video ad spec lists 16:9 and 1:1. Set output width and height to 1920x1080 or 1200x1200.

A 59-second voice-over Short with captions: $0.34 in Sume jobs

Write the script for 59 seconds, not 61: TTS $0.042, captions $0.20, a one-minute render $0.10, total $0.342. The caption estimate covers up to 60 s.

Does a lip-synced dub in your own voice need YouTube's AI label?

YouTube says cloning your own voice for voice-overs or dubs needs no disclosure; a real person made to say what they never said does. How Sume lip sync fits.

X video ad under 30 MB: how many seconds fit at 6,000 and 5,000 kbps

X says keep video ads under 30 MB. At its 6,000 kbps (1080p) and 5,000 kbps (720p) targets that is 40 and 48 seconds. Check yours with Sume video inspect.

54-card deck art at 2:3: $2.36 on Seedream 5 Lite, $5.40 on Banana

Art for a 54-card deck at 2:3 costs $1.35 to $5.40 on Sume depending on the model. GPT Image 2.5 has no named 2:3 ratio; a custom 1024x1536 size is legal.

36 product shots from 36 packshots: about $2.00 on GPT Image 2.5

One reference packshot per SKU, one new scene per call: 36 edits at the listed GPT Image 2.5 medium 2K rate of $0.055625 come to $2.0025. Request and checks.

TikTok AI disclaimer sits at the bottom: keep burned captions higher

TikTok's ad disclaimer shows at the bottom of in-feed video for the whole ad. Place Sume burned-in captions higher with placement.anchor_ratio and test.

30 voice-over variants for an ad test cost $0.171 on Sume TTS

Six hooks, five voices, 120 characters each: 3,600 characters is $0.171 at Sume's $0.0475 per 1,000. MAI-Voice-2.1-Flash lists the same text at $0.054.

LinkedIn landscape video ad maxes at 1920x1080; Sume allows up to 2160

LinkedIn's landscape video range is 640x360 to 1920x1080, but Sume timeline accepts sizes to 2160. Pick 1920x1080 on purpose and verify with video inspect.

Fix one wrong sentence in a voice-over: 130 characters, not 3,000

Redoing a 130-character sentence costs $0.006175 in Sume TTS plus a $0.01 audio join. Re-synthesizing the 3,000-character script costs $0.1425.

20 ultrawide 21:9 website heroes on Sume: from $0.50 to $3.75

Eight Sume image rows list 21:9. Twenty heroes cost $0.50 on Qwen Image, $0.75 on FLUX.2 Pro, $2.00 on Nano Banana 2.1 at 1K, or $3.75 on Nano Banana Pro.

Photo avatar of a real person: when YouTube's AI label applies

A photo avatar scripted to say new words falls under YouTube's 'real person says something they did not' test. How Sume's three avatar inputs map to it.

X video ad: 2:20 at 6,000 kbps is 105 MB, so the 1 GB cap never binds

X allows 1 GB and 2 minutes 20 seconds. At its recommended bitrate the length limit hits first. The math, plus the 9:55 case for approved advertisers.

Real footage trimmed and captioned on Sume: TikTok AI disclaimer?

TikTok requires an AI disclaimer for fully AI-generated or significantly AI-modified media. Which Sume jobs use no generative model, and which ones do not.

LinkedIn allows 25 video uploads in 24 hours: plan a 60-variant test

LinkedIn Campaign Manager caps video uploads at 25 per 24 hours, desktop only. A 60-clip test needs three days. Cut and price the variants on Sume first.

Dub a 3-minute video into Spanish: a 47.8-cent Sume ledger

Detach, transcribe, translate, speak and re-render a 3-minute video: $0.47825 in Sume jobs at 900 characters a minute. Translation is billed elsewhere.

Re-cut a Reel at a new pause threshold: the source never changes

First Draft is reversible; your API cut can be too. Sume media jobs never edit the source, so a new threshold is a new cut list and a $0.10 render.

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.

Rough-cut an imported Reel: the $0.15 import is the biggest line

Importing a Reel costs $0.15, more than the cuts. A 6-trim rough cut totals $0.38; one Timeline render over the same ranges totals $0.27.

Hide jump cuts with alternating punch-ins: one crop copy, N slots

One $0.02 video-filter crop makes a 1.25x punched-in copy. Alternate wide and punched slots at each pause cut for $0.02 total, not $0.02 per cut.

Six podcast ad-read variants at 500 characters: TTS cost and tags

Six 500-character ad reads cost $0.1425 on Sume TTS ($0.02375 each). Tag each take with the metadata field and one Idempotency-Key per variant.

Eight destination teasers, 6 s each: Omni 720p is $6.00

Eight vertical 6-second destination teasers cost $6.00 on Gemini Omni Flash 1.1 at 720p, $3.60 on MiniMax H3 at 768p and $4.80 on H3 Max, priced on Sume.

Character turnaround sheet on a 4:1 strip, sliced into references

One 4:1 Nano Banana 2.1 image on Sume as a four-view character sheet at $0.15 (2K), sliced into four squares and fed back as input_references. Steps and cost.

12 product photos to 4-second clips: price by resolution

Twelve product photos animated into 4-second clips cost $6.00 on Wan 3.0 at 720p. Totals at 480p, 720p and 1080p on Wan 3.0, Omni Flash and Seedance 2.5.

Audiobook chapter of 60,000 characters: three TTS requests, $2.85

One request holds 20,000 characters, so a 60,000-character chapter takes three Sume TTS jobs at $0.95 each, $0.95 in total. Split on paragraphs.