Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
AI video generator for kids: what YouTube says and what to build
Over 200 groups asked YouTube to ban AI videos for kids. What YouTube replied, and how to use Sume for family or classroom clips without chasing views.
Black Friday ads for electronics and furniture: Sume Formats
Adobe forecasts $63.3B in electronics and $33.4B in furniture online this season. Which Sume Formats show a gadget in use or a room before and after.
SSE or WebSocket for AI video progress on Sume? Poll or webhook
Sume has no SSE or WebSocket. mode subscribe is the same 30 s wait as sync. Use async with status polling, the events snapshot, or a webhook. Python example.
Lost a Sume video job id? Recover and download it with the CLI
A restart or timeout does not lose a Sume job. Use sume jobs list, status, watch and download to recover the clip without paying for a second generation.
Gemini Omni scene extension: app, Flow, API or Sume?
Google's launch post lists four places Omni 1.1 Flash runs. Scene extension is not in all of them, and Sume's router does not expose it. Where to go instead.
Black Friday ads for cosmetics and apparel: which Sume Formats
Adobe expects $9.2B in cosmetics and $51.3B in apparel online this season. Which Sume beauty and fashion Formats fit, and which are still, video or try-on.
AI video generator for real estate: which Sume Format?
Sume's 27 catalog Formats include none for property listings. What to call instead for a listing video, and the disclosure test agents face.
Write a YouTube show description from your episode transcripts
YouTube asks you to set a show's details but lists no required fields. Pull transcripts with Sume video inspect at $0.01 a minute and draft from them.
Dub a short into Spanish with an API: detach, transcribe, speak, swap
A Spanish dub on Sume is six jobs you control: detach the audio, transcribe with sentence segments, translate yourself, speak each line, join, and render.
Sume SDK 402 insufficient credits: it is returned, not thrown
Generated Sume SDK calls resolve with data, error and response. Turn a 402 into SumeInsufficientCreditsError with toSumeApiError and stop retrying.
Halloween safety video with an AI avatar for parents and schools
A 21-second three-scene avatar video built from the FDA Halloween tips: costumes, candy and contact lenses. The request body, the cost by tier, and the label.
Video API transitions: six types, one second max, eight in a row
Sume timeline accepts fade, wipeleft, wiperight, slideup, slidedown and dissolve, with a duration of at most 1 second and no more than eight adjacent fades.
Voiceover for shorts: one sentence per shot using TTS sentence slices
Ask TTS for timestamps.words and sentence segmentation and Sume returns gapless per-sentence slices, so each shot in a short gets its own audio file.
Add an AI voiceover to a silent video: TTS, then a timeline render
Add a voiceover to a silent clip with Sume: one TTS job for the narration, then one Timeline 1.0 render that lays the audio over your video.
AI music video with a singer close-up: still plus audio, 5 to 14.8 s
The lip-sync model in Sume's video catalog takes a still and audio of 5 to 14.8 seconds. Split a song to fit, and join the shots on a Timeline.
AI video generator for YouTube: get 16:9 from a Sume Format
Sume's first-party example prompts are vertical. To get a 16:9 YouTube video from a Format, say so in instruction and check the width and height.
Who approves the render: AI copilot or agent for avatar videos?
Tavus says choose a copilot for irreversible actions. A paid avatar render cannot be undone, so the preview, dry run and spend cap decide who approves.
MAI-Voice-2.1 on Foundry and Vercel; Sume's TTS Router is Sonic only
Microsoft lists Foundry, MAI Playground, Vercel and OpenRouter for MAI-Voice-2.1. Sume's TTS Router lists only Cartesia Sonic ids, so check the catalog.
Cyber Monday product videos in bulk: a Sume Format queue
Adobe expects $15.1B on Cyber Monday. How to run one Sume Format over a product list with a bulk queue, concurrency 1 to 16, and recheck failed items.
What a 30-second Wan 3.0 job reserves on Sume: list times 1.25
Sume reserves the provider list price times 1.25 at submit. Work out the hold for a 30-second Wan 3.0 clip and other models in Python.
How many 30-second videos can a Sume Pro key run at once? Wave math
Pro runs 4 generations at once and queues 20 more, so 24 accepted jobs. Use the plan table and a Python function to plan a 50-clip batch in waves.
Express breaks your Sume webhook signature: mount express.raw first
If verifyWebhook returns false in Express, a JSON parser changed the body. Mount express.raw on the webhook route only. Working Node code with the SDK.
Which AI video models take an end frame or reference clips on Sume
Sume's catalog flags show who accepts text-to-video, an end frame, reference images, clips and audio, and who edits video. Grok is image-to-video only.
Make a music video from your own footage with AI: Sume restyle
sume-restyle redoes a clip you own with the same motion and cuts, in chunks of up to 30 seconds. What to supply, what stays, and the audio rule.
Wan 3.0 Apache-2.0: repo license line vs hosted API on Sume
The Wan 3.0 GitHub page shows an Apache-2.0 license line but does not say weights are released. What that does and does not tell you, plus the wan-3.0 id.
How many episodes in a YouTube Shorts season? No official number
YouTube's shows page gives no episode count for a season. Size yours by budget: assembly at $0.10 a minute and captions at $0.20 a job for 6, 8 or 12 episodes.
MAI-Transcribe-2-Streaming 2x faster: what it means for a file
Microsoft says words appear 2x faster than its closest competitor. That is a live-audio claim. For a recorded file on Sume, measure submit-to-result yourself.
Sume webhook retries for 4.5 minutes: dedupe on job_id in Python
Sume retries a webhook up to 10 times, 30 s apart. Make the effect happen once with a claim row keyed on job_id, shown in runnable Python with SQLite.
Deleting a Shorts episode renumbers the rest: skip burned-in numbers
YouTube renumbers other episodes when you edit or delete one. Keep episode numbers out of rendered pixels, or one deletion means re-rendering a season.
Same music under every Shorts episode: Timeline soundtrack settings
Sequential playback means viewers hear episodes back to back. Reuse one music file at one gain and ducking level in every Sume Timeline render of the season.
Add Season 2 to a YouTube Shorts show: renumbering and renders
New episodes land in Season 1 by default. How YouTube numbers seasons, what edits renumber, and how to queue Season 2 renders on Sume without a clash.
Upscale a 90-second video with a 30-second cap: trim, upscale, join
Sume Video Upscale takes up to 30 input seconds per job. Cut a 90-second clip into three, upscale each at $0.009 a second and join them. Total about $1.08.
Public URL or media.sume.com: which Sume media tool takes which
Sume video trim and timeline accept only media.sume.com URLs from your workspace. Captions and video upscale take a public HTTPS URL. Import first.
provider.only on Sume image requests: why other slugs return 400
Porting an OpenRouter-style image call? On Sume, provider.only and order accept only sume; other slugs return 400 provider_not_available. Field rules.
Lyria 3.5 tempo and duration control: Flow Music versus the Sume API
Google says Lyria 3.5 gives easier tempo and duration control in Flow Music. On Sume the same model has no duration field, so you steer length in the prompt.
AI video client timeout: the Sume job still runs and still bills
A timeout on your HTTP client does not cancel a Sume job. Save the job id, poll the polling_url, and cancel only before generation starts. Python example.
Which AI video model makes a 25-second clip? Duration check in Python
Only some Sume video models accept 25 seconds in one request. See each model's duration range and filter a target length in a few lines of runnable Python.
Product launch teaser video with an AI avatar and your product image
Pass a product_image to a Sume avatar clip and the avatar presents it. The per-second rate rises about 5 percent; a 20-second teaser costs $3.88 at standard.
After-hours greeting video with an AI avatar for a small business
A 10-second avatar clip that tells callers when you reopen and how to book. Script size, request body, price at each tier, and why it must say it is AI.
Shortest AI video clip by model: MiniMax H3 4 s, Sume row 5 s
MiniMax lists 4 to 15 seconds for H3. Sume's row starts at 5. Here are the minimum durations in the catalog and how to trim a longer clip.
Ideogram API lists GPT Image and Nano Banana: what Sume's catalog adds
Ideogram's API overview now lists GPT Image and Nano Banana beside Ideogram 4.5. Here is how that compares with the models Sume's /v1/images catalog lists.
4:3 slide image at 1024x768 on GPT Image 2.5: legal, and the price
1024x768 is a legal 4:3 box for GPT Image 2.5 (786,432 pixels). About $0.0113 at medium and $0.0451 at high on Sume.
16:9 insert in a 1080x1920 Short: Timeline fit modes compared
In a 1080x1920 Timeline, cover keeps 31.6% of a 16:9 clip's width, contain shrinks it to 608 px tall, stretch distorts it and blur pads it.
720p landscape to a TikTok 9:16 ad: a 405-wide crop misses 540x960
Cropping 16:9 to 9:16 keeps 31.6% of the width. A 1080p source gives about 608x1080 and clears TikTok's 540x960 minimum; 720p gives 405x720 and does not.
A/B test two hooks in one bulk queue: instruction beats the recipe
Run two opening hooks on one product by sending two items to the same Sume Format. Your instruction is placed after the recipe, so it wins where they disagree.
AI video audio you cannot switch off: Omni 1.1, H3 and H3 Max on Sume
Gemini Omni Flash 1.1 rejects generate_audio false; MiniMax H3 and H3 Max have no toggle. To publish a clip with your own sound, drop the audio with video trim.
Queue-level webhook_url in a Sume bulk body fails: set it per item
A Sume bulk body takes concurrency, items and an optional key. A top-level webhook_url is an unknown field; set communication.webhook_url on each item.
Bulk create returns 429: wait retry-after, resend with the same key
A 429 on a Sume bulk create means the write budget is spent. Wait retry-after, then resend with the same Idempotency-Key; the same payload cannot double-queue.