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
AI change text in image: an edit call with a reference
To change wording inside a picture, send it as an input_references image with a prompt giving the new text. Sume lists edit-capable models.
Edit a high-resolution photo with AI: edit first, then upscale
Sume image edits return at catalog tiers (512, 1K, 2K, 4K), not your photo's full megapixels. Edit with aspect_ratio auto, then enlarge with Image Upscale 1.0.
Text to speech reading a confirmation code digit by digit
To make TTS read a code one digit at a time on Sume, write the transcript with the digits separated, pin a Sonic id, and listen before you ship it.
Hinglish text to speech API: romanized Hindi with language hi
For romanized Hindi or Hinglish on Sume TTS, send language `hi` even though the text is Latin script, and pin a Sonic model id on the Router.
AI video of a celebrity endorsing your product on TikTok?
TikTok's 2026H2 guidelines list a public figure supporting products they have not actually addressed as not allowed. Use an original avatar instead.
TikTok video ineligible for recommendation: AI content rule
TikTok keeps realistic content about public-interest matters out of the For You feed when it is not confirmed as AI or edited. What that means for Sume clips.
Do you have to label a face swap video on TikTok?
TikTok's disclosure list includes a face replaced with someone else's. Sume Avatar Face Swap output is covered: Beta endpoint inputs and disclosure.
Can I make a news-style AI video for TikTok?
TikTok bans AI content made to look like a real news source or a crisis event. A clearly fictional explainer is different. What to avoid, and how to label it.
TikTok unoriginal content and the For You feed: AI batches
TikTok keeps reused material with nothing new out of the For You feed. How to plan templated Sume batches so every video carries something new of its own.
TikTok AI video of a real person without consent: the rule
TikTok does not allow AI likenesses of private figures, including anyone under 18, without consent. How Sume's prompt, props and image avatar inputs relate.
Label an AI background swap on a TikTok Shop video?
TikTok asks for disclosure when a background or object is added or removed in a misleading way. Keep the product itself unchanged and swap only the scene.
TikTok AI parody: spoofs are allowed, realism needs a label
TikTok lists a spoof, meme or dance as allowed humor or art. A realistic AI parody of a person can still need a label. Where the line sits and how to build one.
Demand Gen 9:16 image ad size for YouTube Shorts
Google lists 9:16 Demand Gen images at 600x1067 minimum, 1080x1920 recommended. On Sume, request 1088x1920 (a multiple of 16) and crop 4 px per side.
Google Ads image size 1200x628 and Sume's multiple-of-16 rule
Google's recommended Demand Gen landscape image is 1200x628, but 628 is not a multiple of 16. Request 1200x640 from Sume, then crop 6 px top and bottom.
Demand Gen image max file size: 5 MB, JPG or PNG
Google lists Demand Gen images as .jpg or .png at up to 5 MB (logos 150 KB). Set output_format to jpeg or png on Sume and skip webp for these uploads.
Demand Gen vertical to landscape video: make a native 16:9
Google says Demand Gen will soon turn vertical video into landscape. If you want control over that crop, generate a native 16:9 version and compare.
TikTok Symphony Agent: the same flow through one Sume API run
Symphony Agent turns a product image and a reference video into a brief, storyboard and video. sume-recreate does the reference-to-video part in one API run.
TikTok Symphony Avatar virtual try-on: two Sume Formats
TikTok's upgraded Symphony Avatar joins voiceover, demos and virtual try-on. On Sume, sume-virtual-try-on and sume-product-usage-demo are two callable Formats.
Smart+ Catalog Ads creative: feed Auto-Crawl product videos
TikTok's Catalog Auto-Crawl finds product images and videos on public landing pages. Put videos there: generate one per product from its URL with a Sume Format.
Business Agent for YouTube ads: what Sume makes, what it doesn't
Google's Business Agent answers shopper questions inside YouTube ads. Sume does not build that agent; it makes the product video the ad runs.
Black Friday homepage hero image for Shopify: one set, many sizes
Shopify's BFCM checklist says to put seasonal motifs in the hero image and extend it across channels. Render one reference to each channel's ratio with Sume.
Demand Gen 4:5 image size 960x1200: request it directly
Google lists 960x1200 as the recommended 4:5 Demand Gen image. Both edges are multiples of 16, so a GPT Image 2.5 custom image_size can ask for it exactly.
Demand Gen square 1200x1200: image vs logo file limits
Demand Gen lists 1200x1200 for both the square image and the logo, with different file caps. Request that size from Sume and pick jpeg or png to match.
Demand Gen 4:5 video 1080x1350: the API has 3:4, not 4:5
Google recommends 1080x1350 for 4:5 Demand Gen video, but Sume's video aspect_ratio list has 3:4 and no 4:5. Use the Slideshow Format or a crop step.
HeyGen look packs vs Sume: a new avatar per look
HeyGen's POST /v3/avatars/looks adds looks to an avatar. Sume has no look-pack endpoint: make one avatar per look and steer the scene with a prompt.
AI avatar in Microsoft Teams: Tavus PAL joins, Sume makes clips
Tavus PALs can join Microsoft Teams calls by invite address or Teams URL. Sume renders 4-60 second 16:9 avatar clips you share into a meeting.
Smooth jump cuts: trim, then a short fade between clips
Descript added Smooth all for jump cuts. Via API, trim the clean segments and join them in Timeline 1.0 with a fade of up to 1 second. No AI regeneration.
Replace video audio with an AI voice (and the lip-sync catch)
Sume has no one-call audio swap: detach the audio, transcribe it, make a new voice with TTS, and lay it on a Timeline. Lips will not re-sync to the new voice.
AI music for one section of a video: no duration field
Sume's Music 1.0 rejects duration and duration_seconds. Ask for the length in the prompt, then loop and fade the track to fit one section on a Timeline.
Remove background from video with AI: what Sume covers
Sume has no video background-removal endpoint: RMBG 1.0 takes a still image. What you can do instead is a prompt edit with video_to_video, or a crop.
Use a frame from your footage as a reference for AI video
Pull a still at a time you pick with video frames (unbilled), then pass it as image_url or reference_image_urls to a Sume video model. Steps and limits.
YouTube A/B testing video cuts: build hook variants by API
Build three hook variants of one video as separate files: trim for the hook, Timeline to join hook and body, and a fresh Idempotency-Key per request.
YouTube dynamic thumbnails: generate three options by API
Dynamic thumbnails need three candidate files. Send three Sume image jobs in webhook mode, each with its own Idempotency-Key, and collect the files when done.
Beat sync video editor via API: plan cuts from a stated BPM
Sume has no beat-detection tool. You can ask Music 1.0 for a BPM, then set Timeline 1.0 slot starts and durations as multiples of one beat.
EU AI icon on video: keep burned captions off the label
The EC says the AI icon should sit where no overlay elements exist. Burn captions first, then compose the icon on top in a different band.
How big should the EU AI icon be on a video? No number given
The EC only says clearly visible size and gives no pixels. With Sume Timeline compose, width_ratio sets the badge width as a share of frame width.
AI voiceover for ads: one brand voice across every cut
Make AI voiceover for ads by pinning one voice and voicing each 6, 15 or 30 second cut as its own text to speech request. Fields, fit and cost.
Background music for commercials: generate a bed that fits
Background music for a commercial is an instrumental bed under the voiceover that ends on time. How to brief, generate, cut and duck one with AI.
AI game music generator: one track per level, cut to WAV
An AI game music generator makes each level, menu or boss track from a text brief. How to brief contrasting scenes, get WAV files, and what it costs.
AI voice generator for games: voice every line as a file
An AI voice generator for games turns each dialogue line into an audio file in a character's voice. Voices, engine formats, batch runs and cost.
AI meditation music generator: calm tracks, longer sessions
An AI meditation music generator makes calm instrumental tracks from a text brief. How to prompt one, join tracks into a session, and add a voice.
On hold music for business: make the music and messages
On hold music for a business is a calm track, often with spoken messages, played to waiting callers. How to generate both, in phone-ready formats.
Can AI make a lyric video? Yes, if you time the lines
AI can make a lyric video: pictures under the song, plus each lyric line burned in at the time it is sung. You supply the line timings.
AI Santa video: a personal message with the child's name
Make an AI Santa video in three steps: a Santa character still, the message as speech, then lip sync. One short job per child, billed per second.
Can I use AI images on Pinterest? What the AI label means
Yes. Pinterest labels Pins it detects as AI-generated or AI-edited "AI modified", from metadata or its classifiers, and you can appeal a wrong label.
LinkedIn content credentials: what the CR label means
LinkedIn shows a C2PA icon on images and videos signed with Content Credentials; clicking it shows whether AI was used, the tool, and who signed it.
AI architecture video generator: renders to moving shots
An AI architecture video generator animates a still render: the render is the first frame, the prompt names one camera move. Limits, walkthroughs, cost.
Perfume ad AI video: from one bottle photo to a short spot
Make a perfume ad with AI video: animate a real bottle photo with one move per shot, add a music bed, and check the glass and label in every frame.