Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
MCP traceparent in _meta: tracing a Sume tool call end to end
MCP 2026-07-28 documents traceparent in _meta. Sume's docs don't describe reading it, so correlate with the job id and x-sume-request-id instead.
MCP server notify when work finished: Sume webhooks vs jobs_wait
The MCP roadmap lists push delivery for finished work. On Sume today, MCP agents wait in bounded jobs_wait slices; HMAC webhooks are a REST job feature.
Merchant Center video_link: 6-240 s, 500 MB, raw file URL
The Merchant Center video_link attribute needs 6-240 s, 720p, 500 MB and a raw-file URL. Which Sume video outputs meet each limit, and which need a join.
Meta final-week political ad block: finish video early
Meta blocks new political, electoral and social issue ads in the final week of the US campaign. Submit every video cut, with AI disclosure, before then.
Midjourney inpainting via API: mask_url on GPT Image 2.5
Midjourney's edit model now changes only selected pixels. Sume lists no Midjourney model; its masked inpainting runs on GPT Image 2.5 through mask_url.
MiniMax H3 Max Turbo API: what Sume lists today
Krea added MiniMax H3 Max Turbo on Sep 9. Sume's video catalog lists minimax-h3 and minimax-h3-max, not a Turbo id. What each listed id accepts.
MiniMax H3 Max Turbo price: fal's rates, and the id Sume lists
fal prices H3 Max Turbo separately from H3 Max. Sume's docs list only minimax-h3-max; how to check the catalog, and what that id bills for 5 seconds.
MiniMax music API closed to new users: the Sume Music Router route
MiniMax stopped offering its paid Music and Lyrics APIs to new users on Aug 20, 2026. Sume's Music Router, sume/music-auto, is open: one POST, flat price.
Three Responses subagents, one Sume workspace queue
Responses multi_agent runs 3 subagents by default and they share your tools. Sume accepts extra jobs as queued until queue_full; give each create its own key.
n8n Edit Image text alignment over a Sume-generated image
n8n 2.39 adds horizontal and vertical alignment to Edit Image's Add Image Text. Generate the picture with Sume, then place the exact words on it.
Nano Banana Pro aspect ratio: auto keeps the reference shape
Freepik's changelog says Nano Banana Pro accepts aspect_ratio auto to follow reference images; omitting it stays 1:1. On Sume, omitting is also not auto.
New York synthetic performer ad law and AI avatar ads
NY S8420A requires a conspicuous disclosure of synthetic performers in ads. What it covers, what it exempts, and how to burn a line onto an avatar ad.
Next.js image SSRF fix: narrow remotePatterns for Sume
Next.js patched an Image Optimization SSRF via allow-listed remote URLs. Allow only media.sume.com for Sume images, and never raw provider hosts.
Notion 504 gateway_timeout: check the page before you retry
A Notion 504 gateway_timeout does not mean the write was undone. Read the page, write the Sume video URL once, and dedupe on the webhook's job_id.
OpenAI Agents SDK imageGenerationTool action edit and Sume
imageGenerationTool() takes action: 'generate' | 'edit' | 'auto' in openai-agents-js 0.18.0. To edit with Sume instead, wrap its image route as a function tool.
OpenAI TTS pricing per 1,000 characters, and a 5,000-character script
OpenAI lists tts-1 at $15 and tts-1-hd at $30 per 1M characters. Converted to per 1,000 and a 5,000-character script, next to Sume TTS 1.0's rate.
opencode mcp auth: sign in to Sume, list, debug, log out
Run opencode mcp auth sume to start Sume's OAuth consent, then list, debug or logout. v1.18.33 now reports browser launch failures and redacts debug output.
OpenCode MCP timeout: 5000 ms tools fetch vs Sume jobs_wait
OpenCode's remote MCP timeout is in milliseconds, default 5000, and covers fetching tools. Sume's jobs_wait holds up to 55 seconds per call, a separate limit.
Prompt expansion switch for Wan 3.0 and MiniMax H3 Max on Sume
Krea's H3 Max Turbo has prompt expansion modes. Sume's video model_params allowlist is empty in v1, so Wan 3.0 and H3 Max have no such switch.
Recraft V4.1 Flash API: Sume lists V4, webp, text-only
Recraft V4.1 Flash is live in Recraft Studio and its API. Sume lists recraft/recraft-v4, not a Flash id: webp output, text-to-image only, no references.
Responses steering after a video job started: what Sume does
response.steer does not cancel started tools. A Sume video job past its start runs to completion; jobs_cancel returns 409 job_generation_already_started.
Medical transcription API: what Sume STT does and doesn't
Sume has one speech-to-text route, sume/stt-1.0, with no medical model option. What it takes and returns, so you can decide for clinical audio.
Seedance 2.5 draft mode: a 480p-then-1080p loop on Sume
Higgsfield added Seedance 2.5 Draft Mode. On Sume there is no draft model: render at resolution 480p, pick a take, then re-request at 1080p.
Seedream 5.0 pro bbox and point tags vs region edits on Sume
Seedream 5.0 pro edits a region from <bbox> and <point> tags on a 0-999 grid. Sume lists other Seedream ids; use mask_url on ChatGPT Image 2.5 for regions.
Seedream 5.0 pro layer decomposition vs a Sume Seedream result
Seedream 5.0 pro can split one image into a base plus up to 16 PNG layers. Sume lists Seedream 5.0 Lite, and results are one Sume-hosted URL per image.
Seedream image URL expired after 24 hours: use the Sume copy
BytePlus keeps Seedream image URLs for 24 hours, then clears them. On Sume, read data[].url or the job result URL and store that, not a provider link.
Speech to text custom vocabulary: Sume STT takes a language hint only
Gemini 3.5 Transcribe biases up to 1,000 custom terms. Sume STT has no vocabulary field, only a language_code hint, so fix names after transcription.
Squarespace video background on mobile: make it 16:9
Squarespace says to use landscape video like 16:9 to minimize cropping. Turn a vertical clip into 16:9 with Timeline blur fit, or crop it with Video filter.
Squarespace background video blurry: 1080p and 3 Mbps
Squarespace advises 1080p and at least 3 Mbps for background videos. Sume sets size and fps on its renders but has no bitrate field. What to control.
Squarespace background video not working on mobile: fallback
Phones in low-battery or power-saving mode won't play Squarespace background videos. Add a fallback image; pull a still from the clip with Video frames.
Squarespace background video size: 60 seconds, aim for 40
Squarespace caps an uploaded section background video at 60 seconds and advises under 40. Cut a longer clip to 40 seconds with Sume Video trim first.
Stripe idempotency key length (255) and Sume's key rules
Stripe allows keys up to 255 characters. Sume generation keys are 1-255 printable ASCII and optional; crawl keys are required and capped at 200.
Suno mashup of two songs: what Sume's music API can do
Sume's music models take a text prompt and one optional image, not audio, so no mashup of two songs. You can generate two tracks and join them end to end.
Suno v6 audio and video input vs Sume: text and one image
Suno v6 says you can create with text, audio, images and video. Sume's music request takes a text prompt and one optional image; audio and video are not inputs.
Telegram sendLivePhoto: 10 s, 10 MB and trimming a clip
Telegram's sendLivePhoto video must be 10 seconds or less and 10 MB or smaller. Sume's video trim sets length and frame size; it has no byte-size target.
Temporal activity cancel: Sume job_generation_already_started
When Temporal cancels an activity, a Sume job may already be generating. Cancel returns 409 job_generation_already_started; let it finish and keep the artifact.
Temporal BlobSizeLimitError: pass the Sume artifact URL, not bytes
Temporal Cloud allows 2 MB per payload. Pass the Sume job_id and media.sume.com artifact URL through activities and signals, never video bytes.
Text to dialogue API: continuity between requests on Sume
Sume's TTS has no previous_text field. Keep a line seamless with one longer transcript, or join separate takes with a gapless Timeline audio concat.
Text to speech add pause: Flux, HeyGen and Gemini markers vs Sume
Deepgram Flux, HeyGen and Gemini TTS each use their own pause marker. Sume TTS has none, so use punctuation, speed, or a declared silence in Timeline.
TikTok AI voiceover label: generic TTS vs a real person's voice
TikTok's 2026-H2 guidelines: generic text-to-speech narration needs no label, but AI audio that mimics a real person's voice does. How that maps to Sume voices.
TikTok AI label policy: does anime or cartoon video need one?
TikTok counts anime and cartoons as AI content but says artistic styles need no disclosure. Realistic-looking people or scenes still do. The edge case.
TikTok political ads policy: paid ads banned, with one exception
TikTok bans paid political advertising, including paid creator content. Only official election bodies may advertise procedures such as voter registration.
TikTok Research API documentation: 30-day dates vs Sume date_posted
The Research API takes start_date and end_date up to 30 days apart. Sume's tiktok_search_keyword takes one fixed date_posted value instead.
TikTok Research API access: is_random order vs Sume order
The Research API returns videos by decreasing ID unless is_random is true. Sume's order=play_count sorts a bounded 24-item sample, not a full ranking.
TikTok Research API rate limit: max_count 100 vs Sume's 24
The Research API returns up to 100 videos per call (max_count). Sume's tiktok_search_keyword returns at most 24 items over 3 feed pages per call.
TikTok significantly edited content: which Timeline edits count
TikTok's AI content rules name rearranging clips, cutting phrases and speed changes as significant edits. See which Timeline and trim steps fall on that list.
Twitch 2K clips: trim a 1440p clip without setting output
Video trim's output width and height are limited to 256-2160, so a 2560-wide 1440p clip cannot be conformed. Omit output and the source size is kept.
Twitch clip captions: edit text and timing, burn them in
Twitch is rolling out editable clip captions. For a clip file you edit yourself, Sume burns your own cues with text, start and end, no speech-to-text.