Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Wan 3.0 API: 2–30 second AI video with audio, frames, and references
Call Wan 3.0 on Sume as wan-3.0: 2–30 second clips at 480p, 720p, or 1080p from a prompt, first and last frames, or image, video, and audio references.
Motion control API: animate an image with a driving video
Kling 3.0 Motion Control on Sume animates a still image with the motion of a driving video up to 30 seconds long. Request fields, limits, and price.
Add background music to a video with an API: loop, fade, and duck
Add a soundtrack to a Sume Timeline 1.0 render to mix Sume-hosted music under a voice spine: set its level, loop it, fade it out, and duck it under speech.
Convert a landscape video to vertical 9:16 with the Sume API
Crop a 9:16 window from a Sume-hosted 16:9 clip with video filter, or put the clip in a 1080×1920 Timeline render with a cover, contain, or blur fit.
Split a long video into short clips with the Sume API
Transcribe a Sume-hosted video with video inspect to find cut points, cut each range with video trim, then crop and caption each short clip.
Replace or remove the audio in a video with the Sume API
Remove a clip's audio with video trim's audio: drop, replace it by rendering the clip over a new Sume-hosted spine in Timeline 1.0, or re-level it with gain_db.
Video transitions API: crossfade, wipe, and slide between clips
Add fade, wipe, slide, or dissolve transitions between clips in a Sume Timeline 1.0 render: up to 1 s each, snapped to whole frames, at most 8 in a row.
Image slideshow video API: turn Sume images into an MP4 with music
Turn Sume-hosted images into a slideshow MP4 with Timeline 1.0: stills as video slots, a silent spine for the length, and a looped soundtrack for the music.
Korean subtitles API: Hangul caption styles and fonts without tofu
Burn Korean subtitles with Sume's captions API: pick a Hangul-safe style and font so Korean copy renders in Hangul faces, not tofu boxes.
Auto-generate subtitles API: transcribe, fix the text, then burn
Auto-generate subtitles with Sume: transcribe a clip with video inspect, correct the words, then burn them in with script_text alignment.
Customize captions API: color, position, size, and words per line
Customize burned-in captions with Sume's design object: override color, position, size, and words per phrase on every style except punch and tiktok-green.
Change a video's frame rate or resolution with the Sume API
Conform a Sume-hosted clip's size and fps with video trim's output field or the filter's scale and fps filters, and see how Timeline picks an output frame rate.
AI avatar video API pricing: cost per second and per minute
Sume bills AI avatar video per second by quality tier, with separate rates when you send a product image. Per-minute costs for standard, plus, and max.
Sync vs async API for video generation: Sume's four submit modes
Sume's submit modes are async, sync, subscribe, and webhook. sync and subscribe wait 30 s at most, so for video, submit async and poll, or take a webhook.
Sume TypeScript SDK quickstart: install, client, errors, retries
Install @sume-com/sdk, create one client with createSumeClient, and call typed operations that return errors instead of throwing, with retries built in.
Do failed AI video generations cost credits? Reserve, capture, refund
No. Sume reserves a job's estimated USD cost at submit, captures usage only on completion, and releases or refunds the hold if the job fails or is canceled.
Why did my AI video generation job fail? Reading the job error
A failed Sume job carries a public error: category, stage, retryable, public_reason, and next_action. Where to read it, and what each field tells you to do.
Wait for a Sume job or run to finish in the TypeScript SDK
waitForJob, waitForRun, and subscribeFormatRun poll a Sume job or run until it ends. Here are their default timeouts, the errors they throw, and retries.
Sume webhook not received? How to debug delivery and signatures
When a Sume webhook does not arrive, read webhook_delivery on the job or run, prove your endpoint with a test delivery, then redeliver the real event.
How to cancel an AI video generation job or run with the Sume API
A Sume generation job cancels only before generation starts; Format, Action, and Agent run cancels are idempotent. Routes, responses, billing, webhooks.
Video generation API timeouts: Sume's wait caps, SDK defaults, expiry
A Sume sync submit waits 30 s at most and SDK waits default to 10–20 minutes, but a client timeout never cancels the job. Every limit, and your own deadline.
Sume request_id vs job_id vs run_id: which ID to store and quote
Store the job or run id, dedupe webhooks on job_id or the run envelope's request_id, and quote the req_ request id with the job or run id to Sume support.
Video editing API limits: Sume media tool caps in one table
Source and output lengths, counts, and sizes for Sume's trim, filter, detach, frames, inspect, captions, and Timeline APIs, each linked to its docs page.
Sume developer dashboard: API keys, usage, jobs, billing, playground
Sume's developer dashboard, page by page: create API keys, buy credits on Billing & subscription, inspect Jobs and Usage, and try Avatar in the playground.
What is a video agent? How Sume defines and runs one
In Sume's docs, a video agent is a sandbox Agent that composes generation tools into a post-ready video. Brief it in chat, or call it over HTTP.
How to embed AI video generation in your product with Sume Formats
To embed AI video generation, your server holds one Sume API key and runs a Format per customer, with a derived Idempotency-Key, spend cap, and webhook.
Idempotency keys for AI video APIs: retry without paying twice
An idempotency key makes a retried create return the original run or job instead of a second paid one. How Sume's Idempotency-Key works on each API.
Video API media inputs and outputs: public URLs in, Sume URLs out
Sume generation requests take media as public HTTPS URLs in named fields, with no separate upload step, and return Sume-hosted media.sume.com URLs to store.
How to generate avatar video from the terminal with the Sume CLI
Install the Sume CLI, sign in through the browser, and submit talking avatar videos. Image, Video, and Music 1.0 have no CLI submit command yet.
How Sume API keys work: scopes, auth headers, hosts, and rotation
A Sume API key is a workspace-scoped secret sent as Bearer or x-api-key, never both. Scopes are fixed at creation, and a key works only on its own host.
Video job concurrency and queueing on Sume: limits and queue_full
Sume accepts valid paid jobs as queued and runs them under a plan concurrency limit. A submit fails with 429 queue_full only when the queue is also full.
Sume API errors and rate limits: codes, 429s, and when to retry
Sume API errors share one envelope with a stable code and a request id. Reads and writes have separate per-minute budgets; queue_full is not a rate limit.
Signed webhooks for Sume video runs: events, retries, verification
Sume sends one HMAC-SHA256 signed POST when a Format, Action, or Agent Completion run completes or fails. Verify the raw body and dedupe on request_id.
Safe automation for AI agents that call paid APIs
Keep agents read-only by default, keep secrets out of logs, and on hosted MCP send an idempotency_key, preview with dry_run, and cap with max_spend_usd.
Scheduled AI video agent runs: cron, API triggers, and receipts
A Sume schedule is a saved Agents automation that runs on a cron cadence and returns a run receipt. Author it in the dashboard; start and monitor runs by API.
How to assemble a long-form video with the Timeline 1.0 API
Timeline 1.0 renders one audio spine plus 1 to 200 ordered video slots into one MP4. Every URL must be Sume-hosted; the plan preflight is unbilled.
How to use Sume's Timeline compose and Timeline audio APIs
Timeline compose puts one still and one video in the same frame as a new MP4. Timeline audio joins or splits Sume-hosted audio into reusable files.
Trim, filter, or detach audio from a video with the Sume API
Video trim cuts a range into a new MP4, video filter dims or crops into a new MP4, and audio detach extracts a wav or mp3. Each takes one Sume-hosted clip.
Sume vs Higgsfield: AI ad team or creative suite?
Sume and Higgsfield both run top video and image models. Higgsfield is a creative suite with an agent; Sume's agents also find ads, post them and read results.
Sume vs Kling: Kling's own apps and API, or Kling 3.0 through Sume
Kling sells its own apps and a per-second API for Kling 3.0. Sume offers Kling 3.0 inside one multi-model API and agent. What each publishes, side by side.
HeyGen alternatives with an API: price units, limits, and fit
HeyGen alternatives with an API: Synthesia, Creatify, Argil, Arcads, and Sume compared by price unit, API shape, limits, and live vs rendered avatars.
Sume vs Synthesia: AI avatar video platforms compared
Synthesia makes long avatar videos for business communication; Sume is a video agent with a multi-model API. Plans, API access, MCP, and limits compared.
Sume vs Argil: AI avatar video and video agents compared
Argil makes AI-avatar and story videos with a chat agent, Director; Sume is a video agent with a multi-model API. Avatars, API, pricing, and limits compared.
Sume vs Seedance: BytePlus ModelArk direct, or one API across models
Seedance 2.5 is ByteDance's video model, sold by the token on BytePlus ModelArk. Sume offers Seedance in one multi-model API and agent. Access, limits, pricing.
Sume vs fal: a generative media API or a video agent platform
fal runs 1,000+ image, video, and audio models behind one API. Sume adds a video agent, Formats, and avatars to a multi-model API. How the two surfaces differ.
Sume vs Replicate: running models by API or running a video agent
Replicate runs thousands of models behind one prediction API, billed by hardware time or output. Sume adds a video agent, Formats, and avatars. The differences.
What is a Sume Format? Turn an agent thread into one API call
A Sume Format is a saved video recipe your backend calls by handle and slug. One POST runs it in a fresh sandbox and returns media plus optional typed JSON.
Which MCP server lets Claude Code or Cursor generate video and images?
MCP servers that let Claude Code and Cursor make video and images: Sume, fal, Replicate, Runway, Higgsfield. Endpoints, sign-in, billing, setup.