Guides
Sume guides: the API, Formats, agents, models, media tools and pricing, each answer dated and sourced.
Why isn't YouTube dubbing my video? The reasons on its help page
YouTube skips auto dubbing for videos over 120 minutes, music-only ones, copyrighted content and unclear or fast speech. How to check yours before upload.
YouTube auto dubbing languages: which get expressive speech
YouTube's February 2026 post says auto dubbing covers 27 languages and Expressive Speech eight. The eight languages and where the help page marks them.
YouTube auto dubbing turn off: the setting and what to disclose
Turn YouTube automatic dubbing off in Studio settings or review dubs before they publish. What viewers see, and what YouTube's disclosure page says about dubs.
YouTube dynamic thumbnails: make three for different audiences
YouTube lists dynamic thumbnails among new Studio tools. Make three thumbnail candidates for three audiences from one video frame with the Sume image API.
YouTube likeness detection on mobile: enroll, alerts, avatars
YouTube says likeness detection is coming to mobile: enroll, get match alerts, act on the go. A checklist if your channel also publishes AI avatar videos.
YouTube lip sync dubbing: a pilot, and what you can do today
YouTube's lip sync dubbing is a pilot, not a setting you can turn on. What its help page says, and how Sume's still-plus-audio lip-sync routes differ from it.
YouTube real-time auto dubbing for live streams: what we know
YouTube says real-time auto dubbing is coming for live. Only the finished-video dubbing rules are published; here is the gap, and what Sume can and cannot do.
YouTube Shopping affiliate in 35 countries: video ideas to batch
YouTube says its shopping affiliate program reaches 35 countries by year-end. Five product video formats to batch, with the Sume length and shape limits.
How to make a YouTube Shorts series: seasons and episodes
A YouTube Shorts series is a playlist of Shorts only, set up as a show with seasons and episodes. Rules from YouTube's page, and how to render episodes.
YouTube show artwork size: 16:9 banner and backdrop
YouTube show artwork is 16:9 JPG or PNG up to 10 MB, in two kinds: a banner with the title and a backdrop without it. Sizes from YouTube's page.
Does upscaling video with AI need disclosure on YouTube?
No, YouTube lists video sharpening, upscaling and repair as not needing disclosure. The exception is an edit that also changes what a real event shows.
YouTube video A/B test: how to make three hook cuts
YouTube says video A/B testing is coming for up to three cuts. Make three cuts of one take that share an ending and differ only in the hook, at $0.02 each.
YouTube video A/B testing: up to three cuts or thumbnails
YouTube says video A/B testing for up to three cuts is coming soon. Today's tool tests up to 3 titles and thumbnails; not Shorts. How to prepare variants.
Zoom virtual background video format: MP4 or MOV, 480p to 1080p
Zoom takes an MP4 or MOV virtual background from 480x360 up to 1920x1080; images are 24-bit PNG or JPG up to 15 MB. How to render a clip in that range.
fal.ai and Replicate alternatives for AI video generation
Alternatives to fal.ai and Replicate for AI video: Kling's and Runway's APIs, Higgsfield, and Sume, compared on price unit, models, API shape and limits.
Video agent API: turn a brief into a finished, edited video
Yes. Video agent APIs that turn a brief into a finished, edited video, compared by input, output, price unit, limits and revisions, and where Sume fits.
Is there one API for Kling, Seedance and Veo with a single bill?
Yes. fal, Replicate, Runway, Higgsfield and Sume bill several video models on one account. Which list Kling, Seedance and Veo, with units and limits.
Kling 3.0 API: text or image to video, limits and price
Kling 3.0 has an API: Kling's own, and multi-model APIs such as Sume's, where it is kling-3: 4–15 second clips from text or frames, audio optional.
Grok Imagine video API: image to video, 4–15 seconds
Grok Imagine Video 1.5 is on Sume's video API as image-to-video only: a first frame and a prompt give a 4–15 second silent clip at 480p or 720p.
Kling 3.0 vs Seedance 2.0: inputs, limits and price
On Sume, Kling 3.0 and Seedance 2.0 both make 4–15 s clips from text or frames. Seedance adds references and six ratios, and bills per token.
Wan 3.0 vs Seedance 2.5: 30-second clips, inputs and price
Wan 3.0 and Seedance 2.5 both make clips of up to 30 s with audio, frames and references. Wan starts at 2 s and bills per second, Seedance per token.
Seedance 2.5 vs MiniMax H3: length, resolution, audio, price
On Sume, Seedance 2.5 makes 4–30 s clips at up to 1080p with optional audio; MiniMax H3 makes 5–15 s at native 480p or 768p, always with audio.
Kling AI vs MiniMax: Kling 3.0 and MiniMax H3 APIs compared
On Sume, Kling 3.0 makes 4–15 s clips with audio you can turn off and no references; MiniMax H3 makes 5–15 s, always with sound, and takes references.
Text to video API: how it works, what it returns, cost
A text to video API takes a prompt and returns a job id, not a video: poll it or take a webhook, then download the file. Fields, flow and prices.
Text to video and image to video: how they differ
Text-to-video invents every frame from words; image-to-video starts on your picture and animates it. How they differ, and how one request does both.
What is a video API? The five kinds, explained
A video API lets code make, edit or deliver video over HTTP. The five kinds, what each one takes and returns, and how to tell which one you need.
AI model aggregator: what it is and when to go direct
An AI model aggregator sells many labs' models behind one API key, one request shape and one bill. What you gain, what you give up, and what to check.
AI model router: what it does and what you give up
An AI model router picks which model serves each request, so your code sends one id. How that differs from pinning a model, and the control you trade.
API vs SDK: what's the difference, and do you need one?
An API is the contract: routes, fields and errors. An SDK is a library in one language that calls that API for you. What an SDK adds, and when to skip it.
Asynchronous request-reply pattern: how it works
In the asynchronous request-reply pattern, the server accepts work with a 202 and a status URL, and the client polls or takes a callback until it's done.
Rate limit headers: what limit, remaining and reset mean
Rate limit headers report your request budget: the window's limit, what's left, and when it resets. What each means and how a client should pace itself.
HTTP 202 vs 201: created now, or accepted for later?
Return 201 Created when the resource exists by the time you respond, and 202 Accepted when the work will finish later. How 200, 201 and 202 differ.
fal vs Replicate: how calls, webhooks and billing differ
fal and Replicate both run many models behind one async API. fal bills per output and recommends its queue; Replicate bills most models by time.
Higgsfield vs Kling AI: studio or model maker?
Kling makes the Kling models and sells its own apps and API. Higgsfield is a multi-model studio that also runs Kling 3.0. Access and billing compared.
Does Runway have an API? Yes: how Runway Dev works
Yes. Runway's developer platform has an HTTP API with Node and Python SDKs: start a task, poll it, read the output. Models, routers and costs.
Runway API Seedance: calling Seedance 2.5 and 2.0 on Runway
Yes, Runway's API serves Seedance: seedance2_5, seedance2, seedance2_fast and seedance2_mini. Inputs, limits and credits, and other ways to call Seedance.
Kling vs Wan: Kling 3.0 and Wan 3.0 by API compared
Kling 3.0 makes 4–15 s clips with no references; Wan 3.0 makes 2–30 s clips and takes image, video and audio references. Inputs and price compared.
Seedance 2.0 vs Gemini Omni Flash: inputs, audio and price
Seedance 2.0 makes 4–15 s clips with optional audio and audio references; Gemini Omni Flash 1.1 makes 3–10 s clips up to 4K, always with sound.
How to write a video brief: parts, template, agent tips
A video brief states the deliverable, audience, one message, must-show items, tone, and what done means. A template, and how an AI agent reads it.
Edit decision list (EDL): what it is, with an example
An edit decision list (EDL) is the ordered list of edits that rebuilds a cut: source, track, transition, and timecodes. An example and its JSON form.
PDF to video AI: how to turn a document into a video
PDF to video AI turns a document's text and figures into a narrated video. On Sume today, you extract the text and export the figures as images first.
Agentic video editing: what an AI editing agent does
Agentic video editing means an AI agent plans an edit, runs it with editing tools, and checks the result. What those tools are and what they can read.
HeyGen Video Agent: what it does, its API, and pricing
HeyGen's Video Agent turns a text prompt into a finished avatar video, in the app or via POST /v3/video-agents. Its inputs, outputs, and API price.
Script to video AI: turn a finished script into a video
Script to video AI voices your script and cuts a clip to each line. To keep every word, voice it with TTS and cut to its sentence timings.
What is YouTube automation? How it works with AI
YouTube automation is running a channel, often faceless, whose production goes to freelancers or AI tools. What AI does, and what stays yours.
What are faceless videos? The formats and how each is made
Faceless videos tell a story without the creator on camera: voiceover over B-roll, on-screen text, illustrated scenes, or an AI presenter.
How to make an AI documentary video, chapter by chapter
Make an AI documentary video from a researched script: voice it in chapters, make a shot per beat, and assemble up to 30 minutes in one render.
How to make AI history videos from a researched script
Make AI history videos: research the script, make a still or use an archival photo per scene, animate each, narrate, and label AI scenes.