Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Add a 3-second end card after a clip with Timeline 1.0
In Timeline 1.0 a still is a static hold, so an end card is a second slot after the clip. Add a fade and a soundtrack fade-out on the card.
Facebook catalog: 20 extra images per product from one photo
Meta lets a catalog item carry up to 20 additional_image_link entries. Make extra angles from your real photo with input_references and n.
Facebook catalog image_link: 500x500, 8 MB, JPEG or PNG
Meta's catalog image_link must be at least 500x500, at most 8 MB, JPEG or PNG. Ask Sume for a 1:1 JPEG and measure the file before you add it to a feed.
Facebook catalog product video: 20 per item, 200 MB, direct link
Meta catalog items take up to 20 videos of 200 MB each from a direct download link. Make a clip with Sume and hand Meta the Sume media URL, not a player page.
Faded matte-black video look by API: raise the colorlevels black point
Sume's video filter allowlists colorlevels. Raising the output black point (romin, gomin, bomin) lifts pure black to dark gray for a faded, matte look.
Fix a yellow or blue color cast in a video by API (colortemperature)
Sume's video filter allowlists colortemperature, a Kelvin value from 1000 to 40000 with a default of 6500. Warm or cool a clip and mix it in part.
Flickr video limits: 1 GB, 1080p, 3 free playback minutes
Flickr videos can be up to 1 GB at 1080p. Free accounts play the first 3 minutes and Pro plays 10, capped at 30 fps. Render a fitting clip with Sume.
Cut a 15-second vertical teaser from a trailer with video-trim
After a showcase like Xbox's Tokyo Game Show 2026, studios cut teasers. One Sume video-trim call takes a 15-second range and conforms it to 1080x1920.
Gemini CLI 0.62 MCP tool titles: read a Sume call before approving
Gemini CLI 0.62.0 formats MCP tool call titles as structured signatures. The fields to check on a paid Sume call before you approve it.
Gemini CLI MCP config: malformed JSON vs missing enablement file
Gemini CLI 0.63.0-preview.0 tells a missing MCP enablement config apart from malformed JSON. Check the Sume entry in settings.json when the server won't load.
GIPHY Clips specs: 30 seconds, 9:16 to 16:9, 100 MB, 24 or 30 fps
GIPHY Clips are 30 seconds or less, between 9:16 and 16:9, up to 100 MB at 24 or 30 fps, with sound and no black bars. Render one with Sume.
GitHub social preview 1280x640: generate it with an image API
GitHub's social preview is 1280x640 PNG, JPG or GIF under 1 MB. 1280x640 passes GPT Image 2.5's size rules on Sume; here is the request and the file-size step.
Google Cloud TTS caps requests at 5,000 bytes; Sume counts characters
Google lists 5,000 total bytes per request and says multi-byte characters such as ja-JP count toward it. Sume TTS 1.0 counts characters: up to 20,000.
Google Chirp 3 allows 200 requests a minute; Sume limits by plan
Google lists per-minute request quotas by voice type: Chirp 3 at 200, Studio 500, Standard 1,000. Sume TTS is limited by workspace concurrency on your plan.
Google Vids caption font, position, animation: Sume design overrides
Google Vids lets you change caption font, position and animation. Sume's caption overrides cover colour, size, placement, phrasing and motion, not a Latin font.
Reuse a social video as a YouTube ad: probe the file first
Google says social assets can run as YouTube ads if they meet specs. Probe the clip with Sume's unbilled video-inspect, then trim it if it is too long.
GPT-6 Sol tool calls: use the Responses API to drive Sume
GPT-6 Sol only calls functions in Chat Completions when reasoning effort is none. For Sume's MCP tools, use the Responses API and keep reasoning on.
GPT Image 2.5 Flare: 5 images a minute at Tier 1 vs Sume limits
OpenAI limits Flare to 5 images per minute at Tier 1 and 250 at Tier 5. Sume applies plan concurrency, queue capacity and 429 codes instead. Both tables here.
GPT Image 2.5 largest square: 2880x2880, not 3000x3000
GPT Image 2.5 caps pixels at 8,294,400. A square tops out at 2880x2880; 3000x3000 (9,000,000) is rejected. OpenAI calls sizes above 2560x1440 experimental.
Hookdeck passes gzip bytes unchanged: verify Sume on raw bytes
Hookdeck now forwards binary and gzip bodies byte for byte. Read the raw bytes before parsing and verify the Sume sume-v1 signature over them.
Hume Octave 2 description field vs Sume TTS emotion controls
Hume lists a voice description field; acting instructions are coming soon. Sume TTS 1.0 has generation_config: emotion text, speed 0.6 to 1.5, volume 0.5 to 2.
Hume Octave takes 5,000 characters per utterance in MP3, WAV or PCM
Hume's TTS overview lists 5,000 characters per utterance and MP3, WAV or PCM output. Sume TTS 1.0 takes 20,000 characters and mp3, wav or raw containers.
Inngest retries a failed step four times: key the Sume submit
Inngest's default is four retries after the first attempt, five in all, and side effects are not exactly-once. Give the Sume submit an Idempotency-Key.
Inngest NonRetriableError and RetryAfterError for Sume errors
Map Sume HTTP errors to Inngest: NonRetriableError for 400, 401, 402 and 404, and RetryAfterError with the retry-after header on a 429.
Instacart 3200x800 and 3200x400 banners: what Sume can make
Instacart banners are 3200x800 (4:1) and 3200x400 (8:1). Sume lists 4:1 and 8:1 ratios but no exact-pixel size in v1, so the final crop is yours.
Instacart lifestyle image: 1600x896 passes the 1067x600-1600x900 box
Instacart display ads take a 16:9 lifestyle image of 1067x600 to 1600x900, 1 MB max. Sume's custom size needs multiples of 16, so ask for 1600x896.
Instacart shoppable video ad: 16:9, 3-30 s, from an AI clip
Instacart shoppable video wants a 16:9 MP4 or MOV of 3 to 30 seconds, 500 MB max. Request a 16:9 clip from Sume, then probe the file before you upload.
Instacart video thumbnail 1067x600 to 1600x900 from a clip
Instacart wants a 16:9 JPG or PNG thumbnail of 1067x600 to 1600x900, 10 MB max. Pull a still from your video with the unbilled video-frames route.
Instagram Live ads are live: cut the replay into ad clips
Meta made Instagram Live video ads generally available on September 29, 2026. Cut a Live replay into short clips with Sume's video-trim at $0.02 per job.
JSON2Video 4K costs 4x the credits; Sume Timeline sizes and rate
JSON2Video charges 1 credit per second, 4 for 4K. Sume's Timeline bills $0.10 per output minute and takes edges from 256 to 2160, so no 3840-pixel width.
Keep one color, gray out the rest of a video: chromahold API
Sume's video filter allowlists chromahold, which keeps one key color and turns the rest gray. Set color, similarity and blend, then check the graph for free.
Kickstarter video: 5120 MB main video, optional 9:16 clip
Kickstarter's main video can be up to 5120 MB, and its optional Discovery Mode video is 9:16 vertical, 60 to 90 seconds. Render the vertical clip with Sume.
Lambda durable functions with Pydantic AI: Sume submit as a step
AWS says each model and tool call becomes a durable step that is not repeated after an interruption. Here is how to shape a Sume submit as that step.
Lecture slides beside the speaker: one Timeline compose shot per slide
Timeline compose stacks one still and one video in a frame, up to 300 seconds a shot. Make one stack per slide, then join them in Timeline 1.0.
Listing photo tour in 16:9 and 9:16 from one slot list (Timeline 1.0)
Stills are static holds in Timeline 1.0. Keep one video[] list of listing photos and change only output size and fit for a 16:9 and a 9:16 tour.
LLaDA-Image is open weights: Sume's Image API is a hosted catalog
LLaDA-Image (6B, Apache 2.0, released 2026-09-04) is a download, not an API id. Sume does not list it; use a catalog model with a text-in-image prompt.
Lyria 3 Clip vs Lyria 3.5: which one runs on Sume?
Google lists Lyria 3 Clip as a 30-second model and Lyria 3.5 as minutes long. Sume's Music Router routes lyria-3.5, lyria-3-pro or sume/music-auto.
Lyria 3.5 takes 131,072 tokens; Sume music prompts, 5,000 chars
Google lists a 131,072 token input limit for Lyria 3.5. Sume's music prompt field takes 1 to 5,000 characters. What fits and how to trim.
Lyria 3.5 takes up to 10 images; Sume music takes one image_url
Google's Lyria guide allows up to 10 images as input. Sume's music docs describe one optional public HTTPS image_url. What that changes.
Lyria 3.5 has no Batch API: queue many tracks on Sume instead
Google's Lyria 3.5 page says batch, Flex and Priority inference are not supported. Sume accepts many music jobs and queues them past your concurrency.
Same Lyria 3.5 prompt, different song: why, and no seed on Sume
Google says Lyria results vary between calls. Sume's music API has no seed. How to keep the take you like and generate a few to choose from.
Lyric video captions for an AI song: pass the lyrics as script_text
Lyria 3.5 returns lyrics with the audio. Sume's captions API can take them as script_text to caption a video that carries the song. Steps and limits.
MAI-Voice-2.1: 23 languages and voice matching; Sume takes a voice id
Microsoft says MAI-Voice-2.1 covers 23 languages and matches a voice from a short clip. Sume TTS takes a ready voice id or avatar, not reference audio.
MAI-Voice-2.1-Flash lists 45 ms; Sume TTS is an async job
Microsoft lists MAI-Voice-2.1-Flash at about 45 ms and MAI-Voice-2.1 at about 550 ms. Sume TTS 1.0 is non-streaming: a job with a poll URL or webhook.
Make AI Agent fallback connection retries once: key Sume calls
Make now retries an AI Agent run once on a fallback connection. Keep the Sume Idempotency-Key out of the model's hands so a retried run cannot bill twice.
MCP Enterprise-Managed Authorization is stable: Sume uses OAuth or key
The MCP roadmap calls Enterprise-Managed Authorization stable. Sume's hosted MCP documents two sign-in modes: OAuth with scopes, or an API key.
Meta Creator Marketing Hub: what Sume can do to a creator clip
Meta's Creator Marketing Hub unifies Creator Marketplace and Partnership Ads. Sume cannot join it, but it can trim a creator clip and burn captions on it.
Microsoft Advertising image max 2592x2048: send JPEG, not PNG
Microsoft accepts GIF, JPEG and PNG up to 2592x2048 but converts PNG to JPEG and drops animation. Request jpeg from Sume and skip a lossy surprise.