Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Argil audio upload 50 MB vs Sume Fabric's 10 MB audio URL
Argil takes mp3, wav and m4a uploads up to 50 MB. Sume's Fabric route takes a Sume-hosted audio URL up to 10 MB; H3 Max lip sync wants 5-14.8 seconds.
Argil moderated content rules vs Sume content_policy_rejected
Argil restricts finance, crypto, political and misinformation topics on its own avatars. On Sume a rejected clip fails the job with a public_reason to handle.
ASCI: an AI testimonial ad stays prohibited even with a label
ASCI's September 2026 guidelines keep AI-fabricated endorsements and exaggerated before-after visuals prohibited even when labelled. For avatar ads.
ASCI's three questions: when does an AI ad need a label?
ASCI's September 2026 guidelines ask three questions to decide if synthetic content in an ad needs a label. Here they are, applied to an avatar video ad.
AssemblyAI Sync API: one call, and Sume STT sync mode
AssemblyAI's Sync API returns a short-clip transcript in one POST. Sume STT mode sync waits up to 30 seconds, then returns the job id to poll if not done.
AssemblyAI Sync API file limit vs Sume STT duration_seconds
AssemblyAI's launch post frames its Sync API for short clips. Sume STT 1.0 takes duration_seconds from 1 to 600 and reserves one minute if you omit it.
BFL 24 concurrent requests, 6 for flux-kontext-max, vs Sume
BFL caps concurrent requests at 24 (6 for flux-kontext-max). Sume treats concurrency as a dispatch limit: extra jobs queue until you hit 429 queue_full.
BFL 402 and 429 retry rules, and the same split on Sume
BFL raises on 402 and backs off on 429. Sume splits the same way: 402 insufficient_credits is a stop, 429 queue_full or rate_limited means wait and retry.
BFL polling_url on api.bfl.ai vs Sume status_url
BFL says to always poll the polling_url it returns. Sume's job envelope carries status_url and result_url for the same reason: follow them, do not build URLs.
BFL webhooks vs polling_url, and Sume webhook mode with polling
BFL says webhook users need no polling_url change. On Sume, webhook mode still returns status_url, so verify the signed callback and keep polling as a backup.
Blend two videos together API: what Sume can and cannot layer
Sume cannot blend two videos into one frame: video filter works on one clip, and compose puts one still over one video. Two videos join in sequence on Timeline.
C2PA 2.3 editing history: what trim and filter return in Sume
Content Credentials 2.3 shows clearer edit history such as resizing, markup and redactions. Sume trim and filter return a new MP4; inspect never makes one.
Cartesia accent field: multilingual voices only; Sume uses voice id
Cartesia's accent field is for multilingual voices only and works independent of locale. Sume's TTS request has no accent field: pick a voice id and language.
Cartesia Instant Voice Clone: up to 60 seconds; Sume takes a voice id
Cartesia says to feed an Instant Voice Clone up to 60 seconds of audio on sonic-3.6. Sume's TTS API does not take reference audio; it takes a voice id.
Agent SDK permissionMode omitted: auto mode, Sume gates stay
From Agent SDK 0.3.286 an omitted permissionMode can start in auto mode. Sume's idempotency_key and scope checks run server-side whatever mode you pick.
Agent SDK rewind_conversation and a Sume job: find, then cancel
After rewind_conversation or a priority-now message, the MCP call is handled client-side. A submitted Sume job has its own id: find it with jobs_list.
Claude Code: disable an MCP server mid-session, Sume jobs persist
Switching off an MCP server in Claude Code SDK sessions removes its tools for new calls. Sume jobs already submitted keep running until you read or cancel them.
Managed Agents budget_reached vs Sume generation_spend_cap_usd
A Managed Agents session budget caps spend at list rates and pauses with budget_reached. Sume's generation_spend_cap_usd is a separate required cap.
Claude Managed Agents vault static_bearer for Sume tools
For Sume's hosted MCP in a Claude Managed Agents vault, use a static_bearer credential keyed to https://mcp.sume.com/mcp; OAuth tokens last an hour.
claude mcp add succeeded but no server? Verify Sume with mcp_health
Claude Code 2.1.283 stopped reporting success when the config could not be written. After claude mcp add for Sume, confirm with mcp list and mcp_health.
Cloudflare Workflows deleteBatch: clean up after a Sume job
Cloudflare Workflows can delete up to 100 instances per deleteBatch call. Delete only after the Sume job reaches a terminal event, and keep the job id first.
Code by Zapier 225 requests per 10 seconds and Sume 429s
Zapier lists 225 requests per 10 seconds for Code by Zapier on Pro and Team. Sume has its own 429 rate_limited: honor retry-after and send an Idempotency-Key.
Code by Zapier 10-minute runtime vs Sume's 30-second sync wait
Code by Zapier can run 10 minutes on action steps, but Sume's sync wait caps at 30 seconds. Submit async, keep the job id, and poll instead of holding the step.
Keep one color, rest gray, in a video by API with colorhold
Use colorhold in Sume's video filter to keep one color and gray out the rest of a clip. Free check first, then one encode job on sources up to 300 seconds.
Colossyan callback vs polling, and Sume terminal-only webhooks
Colossyan posts finished or failed to your callback, or you poll every 5 s. Sume webhooks are terminal-only, so keep status_url polling as a backup.
Colossyan intrinsicDurationTrackReference vs Sume scene duration
Colossyan can size a scene to the actor's speech. In Sume avatar videos you set voice.duration per scene, silence beats need it, and the total stays 4-60 s.
Colossyan dynamicVariables vs Sume: fill placeholders yourself
Colossyan swaps {name} placeholders from dynamicVariables. Sume's avatar endpoint has no such field: fill the script yourself, one idempotent job per recipient.
Copyright Office Part 2: prompts alone, and arranging AI video
The US Copyright Office says prompts alone give too little control, but selection, arrangement and modification can count. Which Sume edits arrange.
Creatify Ad Clone credits: 12 per 5 seconds of output
Creatify bills Ad Clone at 12 credits per 5 seconds of output. Sume Avatar Video uses a named quality tier instead, with previews before a full render.
Creatify Aurora 2.0 max audio length: 59.7 s, and how to split
Creatify Aurora 2.0 takes up to 59.7 s of audio; Aurora v1 takes 5 minutes. Sume Avatar Video accepts 4-60 s per job, so split longer scripts across jobs.
Creatify Aurora 2k credits per second: 2.8, audio up to 14.375 s
Creatify Aurora 2.0 bills 0.4 to 2.8 credits per second by resolution, and 2k only works for audio up to 14.375 s. Sume Avatar Video renders at 720p.
Creatify custom avatar lipsync_input and consent video, explained
Creatify custom avatars are built from a lipsync_input MP4 plus a consent video. On Sume, a photo input with an image_url creates a reusable avatar handle.
Cursor custom mode with a pinned skill: install the Sume skill
Cursor lets any skill be a custom mode pinned in the chat. Install the Sume skill with sume skills install; the mode cannot waive idempotency_key or MCP scope.
Cursor /goal with paid Sume calls: what actually caps spend
Cursor /goal keeps an agent on one objective. The goal text is no budget: bound Sume spend with generation_spend_cap_usd, max_paid_calls and dry_run.
D-ID translation result URL: valid 24 hours, then re-fetch
D-ID's translation result_url is valid for 24 hours, so store the file or re-fetch it. Sume media.sume.com URLs do not expire. What to save and when.
D-ID V4 expressives sentiment_id vs Sume's emotion string
D-ID picks a delivery with a sentiment_id preset; Sume TTS takes a free-text emotion string plus a 0.6-1.5 speed multiplier. How each one is set.
Fix flicker in AI video with the deflicker filter API
Brightness flicker between frames can be smoothed with the deflicker filter in Sume's video filter. It will not fix shimmering detail. Check free, then encode.
Discord attachment file_types: image-only option for Sume video
Discord ATTACHMENT command options now accept file_types. Limit a slash command to images, then pass the attachment's public URL to a Sume image-to-video job.
Draw a box on a video with the drawbox filter API
Burn a review box onto a clip with the drawbox filter in Sume's video filter. drawtext is not allowed, so labels need captions. Check first, free.
ElevenLabs Music Audio Reference vs Sume Music's image input
ElevenLabs Audio Reference guides Music v2/v2.5 with a track of about 30 seconds. Sume Music 1.0 takes a text prompt and one optional public HTTPS image URL.
ElevenLabs Music Finetunes vs a reusable Sume Music brief
ElevenLabs Finetunes train on your own tracks in about 5-10 minutes. Sume Music 1.0 has no training step; keep a brand sound with a reusable prompt brief.
ElevenLabs STT 3 GB / 10 hour limit vs Sume STT 600 s jobs
ElevenLabs speech to text accepts files up to 3 GB and 10 hours in standard mode. Sume STT 1.0 reserves up to 10 minutes per job, so cut long recordings.
AI Act standard-editing exemption: trim, filter, caption steps
The Commission FAQ exempts AI assisting standard editing from marking. Which plain edit steps Sume exposes (trim, dim, crop, caption), and what to check.
AI Act deepfake disclosure at first exposure: marking is not enough
Per the Commission FAQ, deployers disclose a deepfake at first exposure in a form people can perceive; the provider's machine-readable mark alone is not enough.
AI Act deepfake definition: the three cumulative criteria
A deepfake under the AI Act needs three cumulative criteria per the Commission FAQ: resemblance, an existing subject, and a false appearance of authenticity.
AI Act artistic or satirical deepfakes: a lighter disclosure
For evidently artistic, satirical or fictional works the Commission says disclose in an appropriate manner that does not hamper enjoyment. Credit or banner?
EU AI icon with a "voices generated with" label on avatar video
The Commission's example pairs the basic EU icon with the text "voices generated with". Here is how to author that line as caption cues on a Sume avatar video.
Facebook Reels API: 30 posts per 24 hours, Instagram allows 100
Meta's Reels Publishing API allows 30 API-published posts in a 24-hour moving period, enforced on video_reels. Here is how to split a 100-item Sume queue.