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
Online course promo video with AI: what to put in it
An online course promo video says who it's for, what they'll learn, what's inside, who teaches it, and where to enroll. How to cut one from AI lessons.
Donor thank you video: one render, each donor's name
A donor thank you video can show each donor's name for the price of one render plus a caption job per name, or say each name aloud at a full render per donor.
AI wedding invitation video maker: art, motion, music, text
An AI wedding invitation video is your invitation art animated into short clips, set to music, with names, date and venue burned on as typed text.
AI Christmas video generator: a greeting that moves
An AI Christmas video is a few animated clips from a photo or a winter scene, an original instrumental, and your greeting burned on as typed text.
How to make AI cat videos: one cat, many shots
To make AI cat videos, approve one still of your cat, start every shot from it, and join the shots under narration. Dancing and talking cats, costs.
AI video generator for church: bumpers, announcements, loops
An AI video generator can make a church's sermon-series bumpers, weekly announcement clips and pre-service loops. How each is made, costs, limits.
AI recipe video generator: step photos, voice, quantities
An AI recipe video turns a photo of each step into a short clip, reads the method aloud, and burns quantities on as text. Steps, costs and limits.
AI fitness video maker: what to generate, what to film
An AI fitness video maker can make the coach, intro, B-roll and on-screen text, but not trustworthy exercise demos. What to film, what to generate.
AI meditation video generator: voice, calm loop, music bed
An AI guided meditation video is a slow narration over a calm visual loop and a soft music bed that dips under the voice. How to build one, and costs.
How to make an AI movie: shot by shot, then the cut
You make an AI movie shot by shot: clips of up to 30 seconds, generated from a shot list, checked, voiced, then cut together. Workflow, limits, costs.
AI movie trailer generator: shots, narration, music, titles
An AI movie trailer is short generated shots, a narrator, music that builds and burned-in title cards, cut together. How to make one, with costs.
AI whiteboard animation generator: blank board to sketch
AI can imitate whiteboard animation: a blank-board first frame, a finished-sketch last frame, the drawing in between. Words go on as captions.
AI product exploded view generator: two frames, real parts
An AI exploded view animation needs two stills: the product assembled and exploded. A video model makes the motion; the parts must come from you.
AI car video generator: from a car photo or a prompt
An AI car video generator animates a photo of your car or invents one from a prompt. How to get a driving shot, what drifts, and what it costs.
AI travel video generator: your trip photos or a prompt
An AI travel video generator either animates your own trip photos or invents a place from a prompt. How each works, what to label, and costs.
1-minute AI video generator: two 30-second clips and a join
No single video request makes 60 seconds. Make two 30-second seedance-2.5 clips and join them with Timeline 1.0 at $0.10 per output minute. Costs and steps.
30-second AI video generator: which models make it in one request
Two models in Sume's catalog generate 30 seconds in one request: seedance-2.5 and wan-3.0. Other text-to-video models top out at 15. Cost at 480p to 1080p.
4:5 or 9:16 for video ads: what each platform's page lists
LinkedIn, Pinterest, TikTok and Meta list different vertical ratios for video ads. No Sume video model lists 4:5, so here is how to crop or size it.
AI avatar for a customer service kiosk: clips, not live chat
A kiosk that answers any question needs a live avatar. A kiosk with known answers can play rendered clips. What Sume's avatar video can and cannot do there.
AI generated video disclosure checklist: TikTok, YouTube, Instagram
A pre-publish checklist for labeling AI video on YouTube and TikTok from their own pages, with a note on Instagram, where no page was read for this post.
AI image for Instagram 4:5 (1080×1350): what the API returns
Instagram portrait is 4:5, 1080×1350, not 4:3. How to ask Sume's image API for 4:5 and why some models return a native size close to it, not exact pixels.
AI music reference artist song blocked: write the brief without one
ElevenLabs blocks downloads of tracks that reference other artists' songs. Describe the sound by emotion, genre, tempo and instruments, as Sume's brief does.
AI product photos: cutout, new scene, upscale, and the cost per SKU
A three-call product photo pipeline on Sume: remove the background, generate a scene from the cutout, upscale the winner. What each call costs per SKU.
AI product photo: change the background to a lifestyle scene
Send the white-background product shot as a reference with an edit prompt and aspect_ratio auto, and Sume returns a new scene. A mask keeps the product fixed.
AI profile picture generator from a photo
Turn one photo into a square profile picture with Sume's image API: send the photo as a reference, ask for a 1:1 result, then optionally cut out the background.
AI voiceover for short videos: 9:16 with voice and music
Make an AI voiceover for a Reel, Short or TikTok: script to speech, clips on the beat of the voice, optional music bed, one vertical MP4.
Amazon Fire tablet video ad specs: 15 s max, 16:9 or 16:10, audio
Amazon's templated Fire tablet video ads allow 15 seconds, 1280x720 or larger, 16:9 or 16:10, .mp4 under 500 MB with AAC audio at 48 kHz. Sume fit.
Amazon Fire TV feature rotator video specs: 1920x1080, -24 LKFS
Amazon lists the Fire TV feature rotator video at 5–21 seconds, 16:9, 1920x1080, no borders, and loudness of -24 LKFS. What Sume can and cannot set.
Amazon Fire TV inline video ad specs: 10 to 30 s, 16:9, 960x540 min
Amazon Ads lists Fire TV inline video at 10–30 seconds, 16:9, 960x540 minimum, 500 MB, 2,000 kbps and audio at 128 kbps or higher. Sume can make the picture.
Article URL to video AI: turn a blog post link into a video
An article URL to video tool makes a short video from a post. On Sume send the article text in input and its images as attachments; the link alone is not read.
Refresh old YouTube thumbnails with AI: a batch method
YouTube says Ask Studio will suggest refreshed thumbnails. To refresh a back catalog yourself, send each old thumbnail to an image API as a reference.
Ask YouTube shopping: get my product recommended, what to make
YouTube is adding a product recommendation guide to Ask YouTube. It has published no ranking rules, so prepare product videos that answer buyer questions.
Can AI make an App Store preview video? Apple's rules
Apple says an app preview uses footage captured on device and shows only content inside the app. A generated clip can't be it, but can be your promo.
Can you use an AI voice on TikTok Shop?
In posted videos, yes: TikTok Shop's 09/02/2026 policy allows AI dubbing and narration. In a LIVE, AI-generated voices are prohibited.
AI thumbnail that matches my channel style: the reference method
YouTube lists channel-matched thumbnail generation as coming. To match your style now, pass your best thumbnails as references and reuse one style paragraph.
ChatGPT image storyboard: make frames with GPT Image 2.5
Make a storyboard with GPT Image 2.5 by API: one call per frame, the same reference images each time, and a prompt that names what stays fixed.
ChatGPT image style transfer: restyle a photo by API
For style transfer with ChatGPT Image 2.5 by API, send the photo as an input reference and name the new style in the prompt. The request and its limits.
ChatGPT Images flyer template: a fill-in prompt for the API
Sume has no flyer template field. Build one as a fill-in prompt with exact text slots, a portrait image_size and a higher quality tier, then check every word.
ChatGPT Images shared prompt: reuse it on your own photos via API
A shared image prompt is only text. Save it in a file, then run it over your own photos with input_references on Sume and match each result to its source.
ChatGPT Images templates (Poster, Merch): are they in the API?
ChatGPT Images 2.5 templates like Poster and Merch are a ChatGPT feature. Sume's image API has no template field, so write the brief as a prompt.
Custom AI avatar from a photo: allowlist or self-serve?
Google gates Live Avatar custom avatars behind enterprise allowlisting. Sume's avatar docs list a photo input on the create route. Request and rules.
Does an AI video API add a C2PA record or watermark to output?
Sume's docs do not say its video output carries a C2PA record or watermark, and trim and Timeline re-encode files. How to check a file and what to do instead.
Does TikTok Shop allow slideshow videos? Not on their own
TikTok Shop's Seller Center page dated 09/17/2026 bars still, looping or scrolling images through a whole posted video. What that means for AI video.
Do I need to label AI voiceover on YouTube Shorts?
Sometimes. YouTube requires a label when a synthetic voice makes a real person seem to say something, and lists AI music as an example. Own-voice clones do not.
Translate a video to another language with AI voice, on time
A translated voice rarely lasts as long as the original. Use TTS sentence segments, the speed control and Timeline audio offsets to keep each line on its slot.
Voice clone 10 seconds AI: what a short sample gets you on Sume
ElevenLabs says Instant Voice Clones can capture a voice from 10 seconds of audio. On Sume you clone in the app, from an upload or a 30-second recording.
EU AI Act Article 50 AI video labeling requirements for creators
Article 50 applies from 2 August 2026: deployers must tell people about deepfakes and providers must add machine-readable marks. What that leaves to a creator.
How to extend an AI video past 30 seconds
Sume has no extend parameter on video models. Chain clips: pull a last frame, use it as the next first_frame, then join with Timeline. Vendor limits too.