Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
X DM video limit: 140 seconds and 512 MB, and how to trim to it
X lists DM video (dm_video) at 140 seconds and 512 MB by default. Cut a clip to length with Sume video-trim, which takes 0.2 to 900 seconds.
X video audio must be AAC-LC, not HE-AAC: check an AI video
X requires AAC Low Complexity audio, mono or stereo, with H264 High Profile and YUV 4:2:0. What Sume's exact trim keeps and re-encodes, and what it leaves.
X video max 1280x1024, ratio 1:3 to 3:1, 60 fps: conform a clip
X video must be 32x32 to 1280x1024, 60 fps or less, ratio 1:3 to 3:1. Read literally, a default 1080x1920 Timeline file is over; conform with video-trim.
YouTube AI label: below the player, and an overlay on Shorts
Since May 2026 YouTube shows one AI label below the player on long-form and as an overlay on Shorts. What a burned-in caption line adds, and what it does not.
YouTube AI label can't be removed: Veo and C2PA cases
YouTube keeps the AI disclosure permanent for its own AI tools such as Veo, and for files whose C2PA metadata says fully generative. What that means.
YouTube added an AI label to my video: how to change it
From May 2026 YouTube may label a video itself when it detects photorealistic AI. If it is wrong, update the disclosure in YouTube Studio; re-editing will not.
YouTube containsSyntheticMedia: the videos.insert field for AI video
videos.insert lists status.containsSyntheticMedia, a boolean on the videos resource. Sume returns the file; you set the flag in your own insert call.
YouTube fhd, qhd, uhd thumbnails in the API: a 3840 AI image
YouTube's API notes fhd, qhd and uhd thumbnail keys for some videos. Sume's ChatGPT Image 2.5 image_size accepts a 3840 edge, enough for a 4K image.
Zapier action timeout at 30 seconds: use Sume webhook mode
Zapier actions time out at 30 seconds, so submit Sume jobs with mode webhook: the call returns a job id at once and Sume posts the result to your URL later.
Zapier Catch Hook 404 when the Zap is off: Sume webhook retries
A turned-off Zap now returns 404 to Catch Hook. For a Sume job that is a failed delivery attempt: it retries up to 10 times, then redeliver or poll recovers.
AI background music for a video: Lyria 3.5 plus Timeline soundtrack
Google lists background music as a Lyria 3.5 template. Generate a bed with Sume's Music Router, then lay it under narration with Timeline soundtrack ducking.
AI birthday song generator by API: Lyria 3.5 on Sume
Google lists custom birthday tracks as a Lyria 3.5 template. Here is how to generate a birthday song with the Sume Music Router and what it costs.
AI brand jingle generator by API with Lyria 3.5 on Sume
Google lists brand jingles as a Lyria 3.5 template. How to brief a short jingle with the Sume Music Router, keep it instrumental or sung, and cost it.
AI ringtone maker by API: Lyria 3.5 plus a Timeline audio cut
Google lists personalised ringtones as a Lyria 3.5 template. Generate the track with Sume, then cut a short wav or mp3 clip with Timeline audio split.
Amazon Polly price per 1M characters, and a 5,000-character script
Polly lists Standard at $4, Neural at $16, Generative at $30 and Long-form at $100 per 1M characters. A 5,000-character script next to Sume TTS 1.0.
Apple Podcasts video uses HLS: what Sume renders instead
Apple Podcasts video is delivered by HLS through hosting providers. Sume renders an MP4 episode with Timeline; it does not produce HLS.
Azure batch takes 10,000 inputs per job; Sume sends one text per job
Azure batch synthesis accepts up to 10,000 text inputs in a 2 MB JSON body. Sume TTS 1.0 takes one transcript of up to 20,000 characters per job.
Azure batch: 95% of outputs within 120 seconds; Sume TTS waits 30
Azure says half of batch outputs finish in 10 to 20 seconds and 95% within 120. Sume TTS sync mode waits at most 30 seconds, then hands you a status URL.
Azure word boundaries in ms vs Sume TTS timestamps in seconds
Azure writes word timings as AudioOffset and Duration in milliseconds, in a separate file. Sume returns words[] with start and end seconds on the job result.
Boost dull video colors by API: the vibrance filter intensity
Sume's video filter allowlists vibrance, with intensity from -2 to 2 and a default of 0. A small positive value lifts muted color; a negative one mutes it.
Cheapest AI video API model on Sume: 5-second clips ranked
Grok Imagine 1.5 is the cheapest 5-second clip on Sume at 480p, then Gemini Omni Flash at 360p and Wan 3.0. Ten models ranked by reserved amount.
Chrome Web Store 440x280 promo tile: generate at 1760x1120
The Chrome Web Store small promo tile is 440x280, below GPT Image 2.5's pixel floor. Request 1760x1120 (exact 4x, same 11:7 ratio) on Sume and downscale.
Chrome Web Store screenshots at 1280x800: request it directly
Chrome Web Store screenshots are 1280x800 (or 640x400), JPG or PNG, square corners, full bleed. 1280x800 passes GPT Image 2.5 rules, so request it on Sume.
Claude Code 2.1.287: MCP server stopped connecting, what to set
Claude Code 2.1.287 added MCP URL prompts. If a server no longer connects, its changelog says to set bareElicitationCapability. Check Sume with mcp_health.
Claude Code 'ask again next time' for reads outside the project
Auto mode now offers a one-time yes for a read outside your working directories. Where Sume results land, and how to keep media inside the project.
Claude Code fork subagents keep plan mode: paid Sume tools
Since 2.1.285 a fork subagent runs under its parent's permission mode and cannot exit plan mode. Two more gates still guard paid Sume MCP tools.
Claude Code headless MCP: a failed first connect is now retried
Since 2.1.283, headless Claude Code retries a remote MCP server whose first connect fails transiently. What to check in a CI run that calls Sume.
MCP tool call ran twice in Claude Code: can Sume bill it twice?
Claude Code 2.1.287 fixed an MCP connector call that could run twice when the server changed protocol version. How Sume's idempotency_key and jobs_list help.
Claude Code /mcp shows no Authenticate for a server: check the URL
Since 2.1.283, /mcp no longer offers Authenticate for a server with no valid URL. Re-add Sume as an http server at https://mcp.sume.com/mcp and sign in.
Sume tool missing in Claude Code: org block or read-only scope?
Claude Code's /mcp list now flags tools your organization blocked. A Sume tool can also be absent because the OAuth session has only mcp:read. How to tell.
Claude Code MCP server shows connected but tools fail after a 404
Claude Code 2.1.283 fixed a brief 404 from a stateless remote MCP server leaving it unusable while shown connected. What to do for Sume's endpoint.
Switch Opus 5.5 and Sonnet 5.5 mid-session: Sume jobs keep running
Claude Code 2.1.287 fixed /model and opusplan switches rewriting earlier MCP tool announcements. Sume jobs live on the server, so a new model can pick them up.
Sonnet 5.5 and a 10-minute render: about 12 jobs_wait calls
A Sume job that takes ten minutes needs roughly 11 to 12 jobs_wait calls at the 55 and 50 second slices. How to keep a Sonnet 5.5 tool loop that short.
Codex network policy now follows redirects: allow Sume's hosts
Codex 0.157.0 enforces network restrictions across redirects and cancels traffic when a policy change revokes access. Which Sume hosts to allow.
Codex 0.158 approval review retry: what it means for a Sume call
Codex 0.158.0 retries an approval review when new user input arrives instead of aborting the pending action. Keep the Sume call's idempotency_key stable.
Cost per SKU for an AI product video: 500 holiday SKUs priced
What one vertical product clip costs on seedance-2.5 at 480p and 720p for 6 and 10 seconds, and what 500 SKUs add up to. Computed from Sume's pricing code.
Cost to transcribe 1,000 hours of audio with an API
1,000 hours is 60,000 minutes: $600 at Sume's $0.01 per minute, in 6,000 or more 10-minute jobs. OpenAI's listed transcription rates give $270 to $1,020.
Creatomate credits per video minute vs Sume's flat Timeline rate
Creatomate lists about 14 credits for a 720p, 25 fps minute and 1 credit per image. Sume's Timeline charges $0.10 per output minute with no resolution tier.
CrewAI 1.15.22 traces human pauses: put the Sume dry run before them
CrewAI 1.15.22 collects human feedback and pause events in tracing. Place a Sume dry_run before the pause so the reviewer sees the cost they approve.
Dailymotion accepts MP4 only: 1080p at 30 fps wants about 4.5 Mbps
Dailymotion accepts MP4 only and publishes bitrates per size, such as 1080p at 30 fps at 4.5 Mbps and 9:16 720x1280 at 2 Mbps. Render a match with Sume.
Deepgram Aura-2 allows 2,000 characters per request; Sume 20,000
Deepgram answers 413 when Aura text passes 2,000 characters. Sume TTS 1.0 accepts 1 to 20,000 characters per request, with a separate 1,200-second audio cap.
Deepgram Aura-2 languages: seven, and how Sume TTS sets a language
Deepgram lists English, Spanish, German, French, Dutch, Italian and Japanese for Aura. Sume TTS takes a language field per request, matched to the voice.
Deno fetch stops retrying fresh-connection POSTs: Sume keys
Deno now retries fetch transport errors only on reused connections. That cuts duplicate POSTs, but a paid Sume submit still needs an Idempotency-Key.
Remove video speckle noise by API: median filter radius
Sume's video filter allowlists median, which replaces each pixel with the middle value of its neighbours. Radius runs 1 to 127; start at 1 and compare.
Edge Add-ons extension logo: 300x300 recommended, 128x128 minimum
Edge Add-ons wants a 1:1 extension logo, 300x300 recommended, 128x128 minimum, per language. Generate 1024x1024 with GPT Image 2.5 on Sume and downscale.
Edge Add-ons 1400x560 promo tile: generate 2800x1120 and halve
Edge's large promotional tile is a 1400x560 PNG, but 1400 is not a multiple of 16. Request exactly 5:2 at 2800x1120 on Sume GPT Image 2.5 and halve it.
ElevenLabs STT edit instructions vs Sume transcribe: what Sume returns
ElevenLabs added transcript-editing instructions up to 2,000 characters to its speech to text. Sume's transcribe endpoint returns a plain transcript.
ElevenLabs dialogue continuity vs Sume TTS segments: what differs
ElevenLabs Text to Dialogue links takes with previous_text and request ids. Sume TTS has no such fields; it returns gapless sentence segments instead.