Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Sume SDK calls resolve with error: make your task throw
Generated Sume SDK operations return { data, error, response } and never throw. In Trigger.dev or Inngest, throw yourself or a failed run looks successful.
Can I distribute AI music through TuneCore? Suno vs Sume tracks
Suno says tracks from its partner model can go out through Believe and TuneCore. That is a Suno feature. What it means if your tracks come from Sume.
Suno's EQ and compressor tips vs Sume Timeline mix controls
Suno published guides on EQ and compression for AI tracks. Sume Timeline has gain and ducking but no EQ or compressor. What you can and cannot do.
Teachable video files: MP4, MOV or AVI, 2 GB each, 1080p
Teachable recommends MP4, MOV or AVI, 1080p at 24 to 30 fps, with 2 GB per file and 20 GB overall. How to render a fitting lesson with Sume.
Telegram custom emoji 100x100: make it from a 1024x1024 image
Telegram custom emoji are exactly 100x100, PNG or WEBP. 100x100 is far below GPT Image 2.5's size floor, so request 1024x1024 on Sume and scale it down.
Telegram sticker size 512: transparent PNG from an image API
A Telegram static sticker needs one side exactly 512 px, PNG or WEBP. On Sume, request a transparent 1024x1024 GPT Image 2.5 PNG, then resize to 512x512.
Temporal Activity ID policies are not a Sume Idempotency-Key
Temporal's Conflict and Reuse policies dedupe Activity IDs inside Temporal. They never reach Sume, so a paid submit still needs its own Idempotency-Key.
Temporal Maximum Attempts 1 and a paid Sume submit
Standalone Activities default to at-least-once retries. Maximum Attempts 1 gives at-most-once, but a Sume Idempotency-Key lets you keep retries safely.
Thinkific video upload: 3 GB, H.264 MP4, 5,000 to 8,000 kbps
Thinkific takes videos under 3 GB, H.264 MP4 at 5,000 to 8,000 kbps, constant 15 to 60 fps, up to 1080p. What Sume can render for it.
Topaz Starlight Fast 3 vs Sume Video Upscale: what you can set
Topaz says Starlight Fast 3 runs at 4x the speed of Precise. Sume Video Upscale 1.0 has its own fast, standard and pro tiers, priced per input second.
Cancelling a Trigger.dev run does not cancel the Sume job
Trigger.dev cancel stops the task and its child runs. A Sume job that already started generating cannot be cancelled, and still bills. Store the job id.
Trigger.dev public tokens show Sume progress without the API key
Hand the browser a Trigger.dev read-only public token for one run while the task holds the Sume key. The Sume key never leaves the server.
Trigger.dev retries and Sume errors: skip 4xx, wait on retry-after
Trigger.dev retries any uncaught throw. Use catchError to skip Sume errors that cannot succeed, and read the retry-after header on a 429.
Trigger.dev replay reuses the payload: key the Sume submit from it
A Trigger.dev replay starts a new run with the same payload. Derive the Sume Idempotency-Key from that payload, not a random id, or a replay bills twice.
Turn a video into a line-art sketch by API with edgedetect
Sume's video filter allowlists edgedetect and negate. Edges come out as white wires on black; negating gives dark lines on white. Modes: wires, colormix, canny.
Udemy video standards: 720p or higher, 16:9, 30 minutes minimum
Udemy needs at least 30 minutes of video to publish a course, HD at 720p or higher, horizontal 16:9. Static slides count as low quality. Render with Sume.
Veo 3.1 only makes 16:9 and 9:16; which Sume video models add more
Google's Veo 3.1 supports 16:9 and 9:16. On Sume, Seedance, MiniMax and Wan add 4:3, 1:1 and 3:4, Kling adds 1:1, and Grok takes no ratio.
Veo 3.1 prompts cap at 1,024 tokens; Sume's Omni at 20,000 characters
Google caps a Veo 3.1 text prompt at 1,024 tokens. On Sume, gemini-omni-flash-1.1 documents a 20,000-character cap. Tokens and characters differ.
Vercel CDN skips Vary: Cookie responses: Sume status proxy headers
Vercel's CDN no longer caches Vary: Cookie responses. For a route proxying Sume job status, send Cache-Control private and honor next_poll_after_seconds.
Vidu movement_amplitude does nothing on Q2 and Q3; Sume uses prompts
Vidu says movement_amplitude has no effect on its q2 and q3 models. Sume has no motion-strength field at all; you steer motion in the prompt.
Vidu off-peak mode: 48 hours for half price, and Sume's cheap tiers
Vidu's off-peak mode generates within 48 hours at half price. Sume has no Vidu model and no off-peak flag; the cheap path is a low-resolution tier.
Vidu Q3 allows 1 to 16 seconds; Sume's shortest clip is 2
Vidu Q3 accepts 1 to 16 seconds. On Sume the shortest clip is 2 seconds on wan-3.0, 3 on Gemini Omni Flash, 4 on Seedance, Kling and Grok, 5 on MiniMax.
Vidyard upload: raw files up to 20 GB, H.264 up to 4K
Vidyard accepts raw video up to 20 GB, then encodes H.264 MP4 derivatives from 360p to 2160p with AAC audio. What to render with Sume.
Vimeo can hide black bars; Sume bakes the right frame into the file
Vimeo's September 2026 Page theme hides black bars on non-16:9 videos. To remove them from the MP4 itself, render the frame with Timeline fit and output size.
Vimeo upload settings: H.264, 10-20 Mbps at 1080p, constant frame rate
Vimeo recommends H.264 High Profile, 10 to 20 Mbps at 1080p, constant frame rate and AAC-LC audio. What Sume can and cannot set for you.
VS Code 1.140 multi-folder sessions: where to put the Sume MCP entry
VS Code 1.140 lets each chat use its own folder or worktree, and reads MCP servers from a global file or a workspace .mcp.json. Put Sume in the global one.
VS Code remote delegation: whose Sume credit is used?
VS Code 1.140's remote delegation tools are off by default and normal approvals still apply. Sume spend follows the credential the session connects with.
VS Code extension icon: 128x128 minimum, 256x256 for retina
VS Code wants an extension icon of at least 128x128, with 256x256 for retina displays. Generate 1024x1024 with GPT Image 2.5 on Sume and downscale to 256.
Which Sume video models accept an audio reference?
Seven Sume video models take reference audio: the four Seedance 2.x ids, Wan 3.0 and the two MiniMax H3 models. Kling, Grok and Gemini Omni Flash do not.
Which Sume video models accept a reference video?
Nine Sume video ids take a video input: the four Seedance 2.x ids, Wan 3.0, both MiniMax H3 models, Omni Flash and Genjutsu. Kling and Grok do not.
Wistia export: H.264 MP4 at 5,000 to 8,000 kbps, 26 GB cap
Wistia accepts files up to 26 GB and recommends H.264 MP4, 5,000 to 8,000 kbps, constant 15 to 60 fps, AAC audio. What Sume can render for it.
Yelp video ads: 2 minutes, 500 MB, and you upload the actual file
Yelp video ads allow up to 2 minutes and 500 MB in MP4, WMV, MOV or AVI, and YouTube or streaming links do not work. Render and trim a file with Sume.
YouTube channel banner 2560x1440: size, 6 MB cap, API request
YouTube's channelBanners.insert wants 2048x1152 minimum, 2560x1440 recommended, 16:9, max 6 MB. 2560x1440 passes GPT Image 2.5's size rules on Sume.
YouTube image posts in Shorts: up to 10 images, 16 MB each, 1:1
YouTube image posts take JPG, PNG, GIF or WEBP up to 16 MB, up to 10 images per post, with 1:1 suggested. How to make 1:1 images with Sume.
Zapier Next Gen Zaps drop the 500-item loop cap: pace Sume
Next Gen Zaps loop past 500 items. A loop of paid Sume submits hits per-minute write budgets and accepted-job capacity first, so size the wave from your plan.
Zapier Next Gen Zaps can pause for a reply: approve before Sume
Put the paid Sume submit after Zapier's new human-reply pause, and key it from the approved record so a double click or a resume cannot submit twice.
Zed 1.22 subagent compaction: keep Sume job ids out of the summary
Zed 1.22.0 compacts subagent threads automatically and lets spawn_agent pick a model. Hand Sume job ids over explicitly so a summary cannot lose them.
Magnified inset callout in video: split, crop, overlay
Sume's video filter has one input, but split, crop, scale and overlay are allowlisted, so a zoomed copy of one region can sit in a corner of the same frame.
Activepieces multipart Content-Length: what body Sume wants
Activepieces 0.91.0 sends known-length multipart with Content-Length. Sume job submits still need JSON; send media as public HTTPS URLs or a PUT upload.
Amazon A+ comparison carousel images: 488x700 portrait, 600x450
The Premium Comparison Carousel needs 3 to 5 product images of at least 488x700 plus 600x450 mobile images. Sume-legal sizes are 800x1152 and 960x720.
Amazon A+ createMedia 201, 200, 409: retry-safe uploads on Sume
Amazon's createMedia answers 201, 200 or 409 on retry. Pair it with one Sume Idempotency-Key per asset so a retried submit never bills twice.
Amazon A+ hotspot image module: make the 1464x600 art first
The Premium Hotspot Image module puts markers on a desktop image of at least 1464x600. Generate it at its final size (1472x608) before placing hotspots.
Amazon A+ media status NOT_APPROVED: poll Sume, then upload
Amazon A+ video media moves through PENDING_PROCESSING, PENDING_REVIEW and AVAILABLE. Two clocks run: finish the Sume job first, then poll Amazon.
Amazon A+ Content API: mediaUrl is not permanent, keep your own copy
Amazon says A+ getMedia's mediaUrl is non-permanent. Re-fetch it, and keep your own copy of finished Sume clips by downloading from the content URL.
Amazon A+ video descriptions per locale vs Sume caption language
A+ updateMedia upserts video descriptions by locale, one of title or descriptions per call. Sume's caption language is only a speech-to-text hint.
Amazon A+ video and image carousel: 2 to 6 panels, one trim each
The Premium Video Image Carousel has 2 to 6 panels, each with its own video or image. Cut one product film into per-panel clips with Sume's video trim.
Amazon A+ video text module: an 800x600 preview from your clip
PremiumVideoTextModule needs a video preview image of at least 800x600. Extract that still from your own Sume clip with the unbilled video frames call.
Amazon Brand Story hero image size: 1464x625 desktop, 463x625 mobile
Brand Story's image-with-logo card needs a desktop image of at least 1464x625 and a mobile image of 463x625. Sizes that pass Sume's 16-pixel rule.