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
Autumn menu photo refresh: 8 dishes, 3 takes on Nano Banana 2
Eight dish photos with a seasonal garnish edit, three takes each, cost $2.40 on Nano Banana 2 at 1K via Sume. Delivery apps may require unedited photos.
Caption 30 clips without a 429: honor retry-after in a Python loop
Submit caption jobs in a loop and wait the `retry-after` seconds on a 429. Reuse the same Idempotency-Key per clip so a retry never creates a second paid job.
Check burned-in caption contrast against WCAG 1.4.3 before rendering
WCAG 1.4.3 asks for 4.5:1 contrast on normal text and 3:1 on large text. Compute the ratio in Python, then set design.colors on a Sume caption job.
Declutter a room photo: mask out furniture on ChatGPT Image 2.5
Remove furniture from a listing photo with a mask_url edit on ChatGPT Image 2.5: $0.065875 per attempt on Sume, so 20 rooms with two attempts each cost $2.635.
Draft with Qwen Image, finish with ChatGPT Image 2.5: 50 heroes cost
Four Qwen Image drafts at $0.025 then one ChatGPT Image 2.5 finish per hero costs $8.29375 for 50 heroes, against $13.175 for four GPT attempts each.
Insert a mid-roll ad into a podcast: Timeline audio split, concat
Split the episode at the break with two ranges, then concat part one, the ad read and part two. Two $0.01 jobs; all parts need the same channel layout.
Lyria 3.5 section timestamps: write a 30-second ad bed prompt
Lyria 3.5 reads section timestamps like [0:00 - 0:10] in the prompt. On Sume, put them in the Music Router prompt and read the section map from result.lyrics.
Mascot to boxed collectible mockup with Seedream 4.5 and 3 references
A boxed-collectible mockup from three references (mascot, box template, shelf) costs $0.05 per image on Seedream 4.5 via Sume; 5 mascots x 4 takes cost $1.00.
WCAG 1.2.2 captions: are burned-in open captions enough?
WCAG 1.2.2 (Level A) covers captions for prerecorded video. Open captions cannot be turned off; burn them in with Sume when one file must carry the text.
Pet Halloween costume portraits: 30 photos, 4 takes each, cost on Sume
Thirty pet photos with four costume takes each, one n=4 call per pet, cost $3.90 on Seedream 4.0 via Sume, which keeps the photo's shape with aspect_ratio auto.
Poem reading video: slow TTS, an emotion string and a ducked music bed
Set generation_config.speed to 0.6 and an emotion string on the TTS router, add a Music Router bed, and render with soundtrack duck_db so the voice stays clear.
Recipe card images for 40 dishes at 4:5: Flux 2 Pro cost and template
Forty 4:5 dish images for recipe cards cost $1.50 on Flux 2 Pro via Sume, $3.00 with one retake each. Add titles in your layout, not in the image.
One video in three languages: a timeline job per language
Keep the same video slots and swap the audio spine per language. A Timeline 1.0 render is $0.10 per output minute, so three 60 s versions cost $0.30.
Show notes from a video: timestamped sentences via Sume STT
Detach a 600-second mono wav, run STT with sentence segmentation, and get timestamped sentences for show notes. Each 10 minutes costs $0.11.
Sticker pack: 12 transparent stickers with GPT Image 2.5 in 3 calls
Twelve transparent-background stickers take three n=4 calls on ChatGPT Image 2.5 with background transparent and cost $0.7905 at the high 1024 rate on Sume.
Teacher's December countdown: 14 cards with read-aloud audio
Fourteen school-day countdown cards on Seedream 4.5 plus a 700-character read-aloud for each cost $1.26 in total on Sume.
Translate caption cues but keep the timings: a reading-speed check
Keep each cue's start and end, swap only the text, and flag lines that become too dense. A short Python check catches it before you pay for the render.
Weekly recap reel from six clips: what 52 Fridays cost on Sume
A 60-second weekly recap from six clips costs $0.42 in Sume media jobs, or $21.84 over 52 weeks. A music bed adds $0.125 once; Agent turns bill separately.
17% of holiday sales come back: answer returns inside the clip
NRF's 2025 report expects 17% of holiday sales to be returned. Here is a four-clip answer set per product, cut from one master for about $0.38 on Sume.
82% cite free returns: a 15-second return-policy clip with cues
NRF's 2025 data: 82% of shoppers cite free returns and 37% of retailers extend holiday windows. Put your policy on screen in 15 seconds for $0.22 on Sume.
9% of returns are fraud: film the pack-out before the box closes
NRF puts return fraud at 9% of returns, with empty boxes and swapped items on its list. A 10-second pack-out clip per order costs $0.02 on Sume to trim.
Flameless candle listing: a doorstep clip that follows CPSC advice
CPSC says to keep candlelit jack-o-lanterns away from doorsteps and landings. Show a flame-free pumpkin in a 12-second clip, $0.22 on Sume.
Costume listing clips: flame-resistant label and reflective tape
The CPSC advises flame-resistant labels, reflective trim and soft props. Show each on camera with three caption cards, about $0.28 on Sume.
Fresh cut, 6 to 8 hours: a tree stand demo built from one phone take
Trees still take up water 6 to 8 hours after cutting, the NCTA says. Film one stand demo take and cut it into three steps for $0.06 in trims on Sume.
Tree lot care cards: 1 quart of water per inch of stem, as clips
The National Christmas Tree Association says a stand needs 1 quart per inch of stem diameter. Turn its care rules into three captioned clips for about $0.66.
Meta video length by placement: Feed 240 minutes, Stories 120 seconds
Meta lists 240 minutes for Facebook Feed, 1-120 seconds for Stories and 5-30 seconds for in-stream. Cut one master per placement with Sume Video Trim.
Audience Network in-stream: 5-30 seconds, sound required, keep audio
Meta lists Audience Network in-stream at 5-30 seconds, the one placement where sound is required. Keep audio when you trim; do not reuse a silent cut.
Halloween night boarding: quiet-room and ID-tag clip for a pet daycare
The ASPCA advises a separate quiet room during trick-or-treating and ID tags on reflective collars. Show both in one 12-second clip, $0.22 on Sume.
Vet clinic Halloween clip: chocolate, xylitol and costume checks
The ASPCA lists chocolate, xylitol candy and ill-fitting costumes as Halloween pet risks. Turn them into caption cards for a clinic reel from $0.22.
DOE's five winter tips as a five-clip series for an HVAC shop
Energy.gov's winter tips: seal windows, check the filter monthly, reverse fans, program the thermostat. Five clips for an HVAC shop cost about $1.10 on Sume.
Reverse the ceiling fan: a 10-second demo clip for a lighting seller
Energy.gov says to run ceiling fans clockwise at low speed in winter. Film the switch and the blades once, then cut and caption a demo for $0.22 on Sume.
Steam store trailer specs: 1080p, 60 fps and 5,000 Kbps from Timeline
Steam trailers can be up to 1920x1080 at 30 or 60 fps and 5,000+ Kbps in .mov, .wmv or .mp4. Sume Timeline renders 1080p MP4 at 24, 25, 30 or 60 fps.
Small Business Saturday for service shops: one offer clip per type
Small Business Saturday is November 28, 2026, and the SBA says to tailor offers by business type. Four service-shop offer clips cost $0.88 on Sume.
Webinar reminders: three 20-second avatar clips per event
Three 20-second 16:9 avatar reminders per webinar cost $11.04 on Sume's standard tier, $14.70 on plus. Twelve webinars a year is $132.48 on standard.
YouTube Shorts max resolution is 1080p: render 1080x1920, not 2160
YouTube lists Shorts at up to 3 minutes and 1080p maximum. Sume Timeline allows up to 2160, but a Short gains nothing from it. Render 1080x1920.
Teacher explainer avatar clips for a semester, with think-pause beats
Thirty-six 45-second avatar explainers for a 12-week term cost $298.08 on Sume's standard tier. A silence scene gives students a think-pause inside the clip.
Agency avatar roster for 25 clients: creation cost, first month
Twenty-five client avatars cost $23.75 to create on Sume at $0.95 each. A first month of four 30-second clips per client is $552.00 on standard.
Meta video ratios 9:16 to 16:9: fit blur or cover in Sume Timeline
Meta's Feed range is 16:9 to 9:16. For a 16:9 clip in a 9:16 frame, Sume Timeline fit is cover, contain, stretch or blur. Pick by what the crop cuts.
SaaS launch week: five 20-second avatar teasers in two ratios
Five launch teasers rendered in 9:16 and 16:9 are 10 jobs. At 20 seconds with a product screenshot that costs $38.80 on Sume's standard tier, $51.60 on plus.
Gift card counter clip: the FTC rule staff and shoppers should see
The FTC says gift cards are for gifts only and that anyone demanding payment by gift card is a scammer. A 10-second counter clip costs $0.22 on Sume.
Shorts tap-to-mute and clear screen: burn captions in with Sume
YouTube's Shorts update adds clear-screen mode, tap to mute and 2x speed. Burned-in captions stay visible; Sume Video Captions sets their style and placement.
Training video policy change: re-render one 15 s module
A policy change in a 45-second avatar training video costs $8.28 to re-render on Sume's standard tier. Three 15-second modules cut that to $2.76.
Reels templates need music and 3 clips: build the match in Timeline
Instagram says Reels templates need music and at least 3 clips. Build the same shape outside the app: a 3-slot Sume Timeline with a soundtrack.
Retail expects 265,000-365,000 seasonal hires: a recruiting clip plan
NRF expects 265,000 to 365,000 seasonal retail hires in 2025, down from 442,000. How to shoot and caption a hiring clip for about $0.36 on Sume.
Realtor open-house reminders: 20 avatar clips, cost and queue by plan
Twenty 15-second open-house avatar clips cost $55.20 on Sume's standard tier. A Free workspace accepts 6 jobs at once and Pro accepts 24, so plan the submit.
Creator daily avatar Short: a 30-day budget, standard vs plus
One 20-second avatar Short a day for 30 days is 600 seconds: $110.40 on Sume's standard tier, $147.00 on plus. YouTube Shorts allow up to 3 minutes.
Reference remix of a clip you own: what Sume's first read returns
Sume reference ingest reads one clip up to 300 seconds and returns shots, on-screen text, audio facts and a strip. What it costs and which errors name the fix.
Replace a clip's soundtrack: detach, Lyria music, re-render on Sume
Detach the audio for $0.01, generate a $0.125 Lyria track, and render a new cut for $0.10 a minute. A 30-second soundtrack swap, priced, plus the rights caveat.