Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Prime Big Deal Days beauty video ads: avatar clips, 4-60 s
Make beauty product ads for Prime Big Deal Days with Avatar Video: scripts must estimate to 4-60 seconds, and product_image is optional. Sizes and prices.
Punch-in zoom on video by API: crop or zoompan, no keyframes
Sume has no auto zoom switch. Use a crop op for a fixed punch-in or the allowlisted zoompan filter in a video-filter graph; there are no keyframes.
Recraft Crisp Upscale vs Creative Upscale, and Sume's upscale
Recraft's Crisp Upscale enlarges without redrawing; Creative Upscale regenerates. Sume's Image Upscale 1.0 takes an image_url and a factor from 1 to 4.
remove.bg API rate limit: 500 per minute, weighted by megapixels
remove.bg allows 500 images per minute at about 1 MP, less for larger inputs. Sume limits requests per minute per key and sends retry-after on 429.
remove.bg bg_color replacement: Sume RMBG gives a transparent PNG
remove.bg's API has bg_color and bg_image_url. Sume RMBG 1.0 takes only an image_url and returns a PNG with alpha, so the new background is a second step.
remove.bg crop and roi parameters: what Sume RMBG does instead
remove.bg has crop, roi, crop_margin, scale and position. Sume RMBG takes an image_url only and rejects other fields, so cropping happens before or after.
remove.bg PNG over 10 MP unsupported: Sume RMBG limits
remove.bg does not support PNG above 10 megapixels; use WebP or ZIP up to 50 MP. Sume RMBG returns PNG with alpha and caps compressed input at 20 MiB.
remove.bg type parameter (car, product, person) vs Sume RMBG
remove.bg's API has a type parameter and an X-Type header. Sume RMBG 1.0 has no foreground-type hint: send an image_url and Sume selects the model.
Replicate cost estimate before running vs Sume dry_run preview
Replicate lists cost estimates on each model's page. On Sume, send dry_run=true on a paid MCP tool to preview admission and cost without submitting the job.
Replicate Wan 3.0 30% off this week: what Sume bills
Replicate's pricing page shows a one-week 30% banner on Wan 3.0. A Sume video job reserves at provider list times 1.25 and reports usage.cost.
Runway autobilling: how it works, and Sume's manual top-up
Runway autobilling checks hourly, recharges below a threshold, at least 1,000 credits ($10), and stops after three failed charges. Sume top-ups are manual.
Do Runway credits roll over? Max plan: one month
Runway's pricing page says Max credits roll over for 1 month. Sume's plan descriptions list no monthly credit allotment, so there is no plan roll-over.
Seedance 2.5 extend mode without ratio: how to continue a clip on Sume
Runway's extend mode needs promptText and no ratio. Sume has no extend flag: continue a clip with a first_frame image or a Video Router video_url edit.
Seedance 2.5 references only, no prompt: Sume still needs a prompt
Runway's Seedance 2.5 text-to-video can omit promptText when a reference is given. On Sume the video `prompt` field is required, so send a short one.
Runway task failure codes: which to retry, which not to
Runway says never retry SAFETY or ASSET.INVALID failures, retry INTERNAL ones with a delay. The same triage on Sume: 429 with retry-after, new keys for runs.
AI presenter for a SaaS demo video, with or without a product image
For a SaaS demo, omit `product_image` for a productless avatar video, or add one. Each Sume avatar job runs 4 to 60 seconds, so longer demos are split.
AI video background swap for a fashion lookbook with Seedance 2.5
Seedance 2.5 describes green screen editing that swaps a background and keeps the subject. On Sume, send the garment clip as a video reference, 4 to 30 seconds.
Seedance 2.5 green screen editing: what Sume can do
ByteDance says Seedance 2.5 improves green screen editing. Sume's docs document an edit mode only for Gemini Omni Flash 1.1; Seedance takes video references.
AI workout video generator: Seedance 2.5, 4 to 30 seconds
For a workout demo, one Seedance 2.5 request runs 4 to 30 seconds on Sume, with video and audio references; most other catalog models stop at 15 seconds.
Speechmatics Linden for voice agents vs Sume batch STT jobs
Speechmatics announced Linden for voice agents. Sume STT is a bounded batch job with a webhook, not a live stream, so live agents need streaming.
Suno free plan: 50 credits a day, no downloads. Sume's Free plan
Suno Free gives 50 credits per day with no monthly song downloads or commercial rights. Sume's Free plan has no credit allotment and covers image generation.
Synthesia auto top-up vs Sume: manual dashboard top-ups
Synthesia now offers automatic credit top-ups. Sume top-ups are a manual Stripe-backed dashboard action; a low balance fails at submit, not mid-job.
Synthesia bulk download of 20 videos vs Sume result URLs
Synthesia can bulk download up to 20 videos as .mp4 files. On Sume you list avatar-video resources and fetch each job's result for its media.sume.com URL.
Synthesia Interactive Avatar API vs Sume rendered avatar clips
Synthesia headlines a live Interactive Avatar API. Sume avatar video is script-driven and rendered as a job: submit, poll, then fetch the clip.
Synthesia animated scene preview vs Sume first-frame stills
Synthesia previews one scene with a fully animated avatar. Sume previews are first-frame stills with no motion, approved before the full render.
Synthesia avatar sharing vs Sume workspace-scoped avatars
Synthesia shares an avatar's base person with teammates or a workspace. Sume API keys are workspace-scoped, and avatars are referenced by handle.
TikTok Ad Network asset specs: banner 640x100 and where Sume stops
TikTok Ad Network wants video at 1280x720, 720x1280 or 720x720 and banners at 600x500, 640x200 or 640x100. What Sume renders natively and what needs a crop.
TikTok carousel ad specs: 2-35 images and three sizes
A standard TikTok carousel takes 2 to 35 JPG or PNG images at 1200x628, 640x640 or 720x1280. Here is how to map those onto Sume image settings.
TikTok carousel ad music: mp3 required, silent on Ad Network
TikTok carousel ads need an .mp3 of 2 s or more, up to 10M. Library music is silent on Ad Network placements, so upload your own file there.
TikTok Global App Bundle image ad sizes: 9:16, 16:9, 1:1
TikTok's Global App Bundle image ads need 9:16 at 720x1280 or more, 16:9 at 1280x720 or more, or 1:1 at 640x640 or more, as JPG or PNG within 100 MB.
TikTok photo post API: 35 image URLs, PULL_FROM_URL, cover index
TikTok's photo post endpoint takes up to 35 public image URLs by PULL_FROM_URL and a photo_cover_index. How to plan the generated-image batches that feed it.
TikTok photo post API: is_aigc label and auto_add_music
Set is_aigc to true on a TikTok photo post of generated images to add the AI-generated tag. auto_add_music is direct post only. And the audit rule.
TikTok photo post title length: 90 runes, description 4000
TikTok's photo post API caps the title at 90 UTF-16 runes and the description at 4000, unlike video posts. How to count them and where Sume fits in.
Video render priced per minute: 61 seconds bills two minutes
Sume Timeline bills per ceil(output minute), so a 61-second render counts as 2 minutes. A worked rounding table for 59, 60 and 61 seconds.
Fade out music at the end of a video: two fades, two caps
In Timeline 1.0, soundtrack.fade_out_seconds fades only the music bed (max 10 s). output.fade_out_seconds fades the whole render (0 to 5 s). Which to use.
Crossfade longer than 1 second: the Timeline transition limit
Timeline 1.0 transitions are capped at 1 second and 50 percent of the shorter neighbouring clip. Longer ones return transition_too_long. What to do instead.
Use audio from a TikTok or Instagram link in your video
Sume imports a public TikTok or Instagram URL, detaches its audio as wav or mp3, then lays it under a Timeline render. YouTube links are rejected.
Video starts on a black frame: fix the first Timeline segment
A render that opens on black usually has a fade or a late first clip. Timeline 1.0 refuses a first start other than 0 and any first-segment transition.
WhatsApp audio message format: AAC, MP3, OGG Opus mono, 16 MB
WhatsApp accepts AAC, AMR, MP3, M4A and OGG (Opus, mono) up to 16 MB. Sume's audio detach returns mp3 or wav, so mp3 fits; ogg needs another tool.
WhatsApp Cloud API video message size limit: 16 MB, H.264 and AAC
WhatsApp video messages take MP4 or 3GP up to 16 MB, H.264 video and AAC audio only. See what Sume's exact trim outputs and what you still check yourself.
WhatsApp Cloud API media ID expiry: 30 days, URL 5 minutes
WhatsApp media IDs from the API expire after 30 days, webhook IDs after 7, and a media URL works for 5 minutes. Keep your own durable source, not the ID.
YouTube A/B testing three cuts: render the variants by API
YouTube Studio can test up to three cuts of a video. To make the cuts, trim one source three ways and render each with Timeline; here is what that costs.
YouTube paid promotion label on an AI-generated sponsored video
A sponsored AI video on YouTube needs the paid promotion button in video details. Sume does not set it; you set it in YouTube Studio when you upload the file.
Trim pauses and reorder clips by API, like YouTube chat editing
YouTube's conversational editing trims pauses and reorders for pacing. By API: inspect the clip for free, trim ranges, then reorder slots in a Timeline spec.
Faceless YouTube channel from outlier videos: what Sume covers
Sume's trending search is TikTok-only, so find YouTube outliers in YouTube Studio. The long faceless build is one Timeline of up to 1,800 seconds.
AI Act deployer for an agency: the legal person, not each hand
Per the Commission FAQ, a company stays the deployer when contractors or freelancers operate the AI system for it. How that maps to one Sume workspace key.
AI Act Article 50(1) and a rendered avatar video: the test
Article 50(1) needs a system built for genuine two-way exchange. A rendered, script-driven avatar video is one-way; check the four criteria. Not legal advice.
AI Act Article 50(3): what Sume video inspect returns
Video inspect returns probe facts, stills and optional STT. The FAQ ties Article 50(3) to emotion recognition; the inspect docs list no such output.