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
Mintegral video specs: MP4 only, 200 MB, 6, 15, 30 or 60 s
Mintegral wants MP4 up to 200 MB, 1080x1920 and 1920x1080 recommended, 6/15/30/60 s lengths, and a 1200x627 image as the endcard. Cut those lengths with Sume.
Mobile game ad cutdowns: one master to 6, 15, 30 and 60 seconds
Mintegral recommends 6/15/30/60 s, Unity and Axon cap at 60 s, Liftoff at 180 s. Cut one portrait master to each length with Sume's trim API for $0.02 a job.
Newsletter issue to a vertical recap video for Christmas week
Christmas Day is Friday, Dec 25, 2026. Turn a newsletter issue into a 30-second vertical recap with three avatar clips and a Timeline join, no new writing.
One edit, three Google Ads sizes: 16:9, 9:16 and 1:1 on Timeline
Google lists 1920x1080, 1080x1920 and 1080x1080 for 15-second video. Render one Timeline edit three times with fit set per shape. Cost: $0.10 per render.
Open house invite video for Thanksgiving weekend, from listing photos
Thanksgiving is Nov 26, 2026, so the open house weekend is Nov 28 and 29. Turn six listing photos into one vertical invite with the date and address burned in.
Podcast episode teaser for Thanksgiving week: trim, caption, post
Thanksgiving is Nov 26, 2026. Trim a 30-second moment from an episode video, burn in captions and add a title card, with limits on rights and accuracy.
Recraft Flash draft then Refine: the closest rerun on Sume
Recraft's Refine regenerates a Flash draft at higher quality while keeping composition. Sume has no refine call or seed, so here is the nearest honest workflow.
Seedream 4.5 edit: swap a product with up to 10 references
fal describes Seedream 4.5 edit as multi-reference product replacement and text overlay with no masking tool. The same shape of call on Sume.
Snapchat AI Clips make 5-second videos; do it outside Snapchat
Snap's AI Clips turn a photo into a five-second video inside a Lens. Here is how to get the same photo-to-clip result as a file you can post anywhere.
Spotify in-feed video ad specs: 30 s, three ratios, 500 MB
Spotify in-feed video takes up to 30 s in 9:16, 16:9 or 1:1, MOV or MP4 up to 500 MB, no black bars, no leaders. How to cut it and avoid bars with Sume.
Spotify in-stream video ads must have sound: no silent files
Spotify's in-stream video spec says all files must include sound and no silent videos are accepted. Check a clip has audio and add a track before upload.
Thanksgiving week release notes video for SaaS: three avatar clips
Thanksgiving is Nov 26, 2026. Ship release notes as three short avatar clips, one per change, with captions, and add a plain-text fallback for each.
TikTok Shop video: no PDP screenshots, 50% rule, check with frames
TikTok Shop video rules bar screenshots, stills, slideshows and animated figures over half the screen. How to check a finished clip with Sume video frames.
Unity Ads video specs: 60 s, H.264 MP4, 100 MB cap
Unity's user acquisition docs set video at 60 seconds or less, H.264 in MP4, 16:9 or 9:16, 100 MB max, and an end card. What Sume's trim step can and cannot do.
VAST video ads: Microsoft wants 500, 1200 and 2500 kbps files
For third-party VAST video, Microsoft Invest recommends three bitrates and 15 or 30 s on Google inventory. What a Sume master gives you and what it lacks.
Google Ads video action campaigns: 10 s minimum, three ratios
Google's spec page gives video action campaigns a minimum length of 10 seconds in 16:9, 9:16 and 1:1. Cut a master to length and ratio with Sume.
Video ad end card images: Mintegral, Liftoff, Unity and Axon sizes
End card image sizes differ: Mintegral 1200x627, Liftoff portrait 1080x1920 up to 1 MB, Axon page image 270x480 minimum. Make them with Sume's Images API.
Year-end client recap video: twelve photos, one Timeline render
Christmas Day is Dec 25, 2026. Build a 36-second thank-you recap from twelve project photos with Timeline holds, caption cues and no invented numbers.
YouTube ad length limits in DV360: masthead 10 s, Shorts 5 s
DV360 lists YouTube lengths: bumper 6 s or less, non-skippable 7 to 15 s, Shorts 5 s or more, masthead 10 s or more. How to cut to each with Sume.
YouTube auto dubbing skips videos over 120 minutes: dub in chunks
YouTube auto dubbing is unavailable for videos over 120 minutes. A script can cut a long file into trims of up to 900 seconds, then dub each piece.
3-minute AI presenter video: three 60-second clips plus Timeline
A 180-second presenter video built from three 60-second avatar jobs costs about $44.10 on Plus plus $0.30 to join them with Timeline, at listed rates.
AI airport sign photos: set arrows and words in code, not the model
Image models still bend arrows and misspell wayfinding text. Generate a sign with no text, then set the exact arrows and words in Pillow. Runnable script.
AI outfit builder: three garments, one model, reference order
Put a top, trousers and shoes from three separate product photos onto one model in a single gpt-image-2.5 edit on Sume, with a reference order that holds.
AI presenter video for job postings: 25 roles, 20 seconds each
25 twenty-second hiring clips from one recruiter avatar cost $122.50 on Plus or $92.00 on Standard, plus $0.95 once, at Sume's listed rates.
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.
App Store app preview: one 886x1920 master covers four iPhone sizes
Apple lists 886x1920 for the 6.9, 6.5, 6.3 and 6.1 inch iPhone app previews. Cut one 15 to 30 second master with Sume video trim, then probe it.
One voice in 23 languages: a test matrix to run before you commit
MAI-Voice-2.1 claims one voice with a native accent in 23 languages. Build a 23-line audition matrix and cost it before you promise it to a market.
Clipper channel with permission: does YouTube still count it?
YouTube's page says promoting others' content is not allowed even with permission. What a clipper channel must add, plus trim and caption mechanics.
Unreadable captions on bright Reels: dim 0.45, check for free
Burned-in captions vanish on bright footage. Sume video filter dim 0.45 darkens luma; the /video-filter/check endpoint validates the program at no charge.
ChatGPT Try On saves a reference photo: what your own flow should keep
OpenAI's Try On keeps a reference photo you can delete. If you build your own try-on on Sume, decide what you store, what you send, and what you link back.
Best-of compilation of your own Shorts: does it count as original?
YouTube lists compilations with no original content as non-original. For your own clips the pages are silent. What to add so a best-of earns its place.
Does YouTube's originality update demonetize Shorts?
As reported, the Oct 1 change affects Shorts recommendations while monetization stays under the existing reused-content policy. What that means.
Dub a video, keep the music: Sume has no stem splitter, so do this
Sume can detach a video's audio and re-voice a script, but its docs list no vocal and music separation. A clean workaround with a new music bed and ducking.
Edits assistant: US-only, daily cap, and what Sume covers instead
Edits assistant rolled out Sept 30 2026 to US users with a free daily prompt limit. What Sume docs cover for the media steps, and what they do not.
Edits beat markers: cut to the beat with Sume Timeline start times
Edits auto-detects beats in your audio. Sume docs describe no beat detection, but a known BPM gives exact cut times for Timeline video slots. Script included.
Edits teleprompter script: check the recorded pace with video inspect
Instagram Edits has a teleprompter. After recording, Sume video inspect returns a transcript at $0.01 per audio minute, so you can compute words per minute.
Reel end card: trim the last 3 s, then overlay a still
Sume timeline-compose holds a still for the whole clip, so an end card on the last 3 seconds needs a trim first. Trim, compose, then join in Timeline.
Flat-lay garment photo to on-model image with GPT Image 2.5
Turn a flat-lay or hanger photo into an on-model image with openai/gpt-image-2.5 on Sume: reference order, aspect ratio auto, and a quality ladder.
Virtual try-on for a sofa in a room photo: image edit with Sume
ChatGPT Try On covers clothes and accessories. For a sofa or wall art in a room photo, use gpt-image-2.5 with input_references and an optional mask_url on Sume.
Gameplay Shorts after YouTube's originality update: what pages say
YouTube's reused-content pages don't name gameplay. What they say about your own footage plus commentary, and how to cut highlight Shorts where you talk.
Griffin-Lite safety hold: what to prepare now for AI video calls
Tavus is holding Griffin-Lite over deception risk. Three things to prepare before any realistic AI presenter ships: consent, disclosure and a recorded fallback.
Carousel music is blocked with video slides: use a frame still
Instagram says music cannot be added to carousels with videos. Pull a still from each video slide with Sume video frames to keep the music option.
Per-slide carousel captions: pair each image job with its caption
Instagram added per-slide carousel captions. Keep each slide, its caption and its Sume image job in one manifest so a retry never mismatches. Script included.
Instagram posts in Google: draft the caption from the transcript
Public pro-account posts can appear in Google. Write the caption from what the video says; Sume video inspect returns a transcript at $0.01 per audio minute.
Instagram Replace Audio on a published post, or re-render with Sume
Instagram added audio replacement on published feed posts. Sume can render a new soundtrack but cannot feed it into that flow. Which route keeps what.
Reel safe zones: set compose margin_ratio to keep text clear
Instagram Edits shows safe zones in the editor. For a plate added in code, Sume compose overlay margin_ratio (0 to 0.45) sets the distance from the edge.
Lipstick shade preview with image edit: what a render cannot promise
A shade preview from gpt-image-2.5 on Sume is a picture, not a colour match. How to build it with a mask, and what to tell shoppers.
Ad from one product photo: a 4:5 still, a 9:16 clip and a 6 s cutdown
Three Sume calls turn one packshot into a 4:5 feed image, a 9:16 UGC-style clip and a short cutdown. Settings, order and what to check at each step.