Amazing explainer videos, under a minute

Type a prompt or drop a document. Sketchie writes the script, draws every scene, and narrates it in your language and your style. For a fraction of what explainer videos cost anywhere else.

Get Started
Drop in a document, audio, video, or a link. PDF, Word, PowerPoint, MP3, MP4, or any article link. Sketchie turns it into an explainer video.
Made with Sketchie

Explaining things is brutal. The doc nobody reads, the recording nobody watches, the deck that puts the room to sleep. Sketchie is the shortcut: type it, watch it draw itself in under a minute, tell it what to change.

Feed it anything. Ship it anywhere.
Feed it PDF Word PowerPoint Markdown
Export-ready for YouTube TikTok Instagram LinkedIn X
Agents Claude Cursor + any MCP client
How it works

Prompt in. Video out, in under a minute.

1

Drop anything in

A prompt, a PDF, a Word doc, a Markdown file, your product docs. Sketchie reads it and writes a script built on story structure.

2

Watch it draw

Every element draws on stroke by stroke, timed to the exact word of narration it belongs to. The biggest retention lever in the research.

3

Fix what is off

Open the scene list, click a scene, edit the text, visual, or narration. Sketchie re-renders that scene only, in seconds. Cents, not another full video.

4

Ship it

Export MP4 in any of three aspect ratios, or pull the scene graph through the API and do whatever you want with it.

recursion-explainer.mp4  · 6 scenes · 1:12
Scenes, not takes

Fix one scene. Not the whole video.

Sketchie’s videos are living documents. Every scene is addressable and editable after generation. Spot a wrong sentence, open the scene, fix it, and the video is corrected in seconds.

  • Edit scene headings, narration, labels, and icon styling
  • Move between scenes with Previous and Next controls
  • Describe a bigger change in plain language when fields are not enough
  • Save your edits and re-render the updated version
Why Sketchie

Built different where it counts.

A full video in under a minute.

Script, scenes, narration, and word-level timing, all generated while you watch. The gap between "we should explain this" and a finished video is now shorter than a coffee refill.

Built on learning science.

Progressive drawing beats finished diagrams for retention, attention falls off after 6 minutes, ending with a question beats a summary. We wired those findings in as hard rules with an eval harness behind them.

Length you control.

Set length in 30-second steps, or let Sketchie pick. Videos default to 6 minutes or less because that is where the engagement data says attention lives. Longer material becomes a chaptered series.

A fraction of the usual cost.

Plans start at $9.99 a month for 40 minutes of video. An agency or freelance animator charges $100 to $900 for a single explainer and takes weeks. Edits re-render one scene for seconds of minutes, not a whole regeneration.

API and MCP, day one.

One endpoint in, video plus editable scene graph out. Plus an MCP server, so any AI agent can generate and edit explainers directly.

Sticky, not viral

We optimized for whether they remember it tomorrow.

Fast and cheap only matter if the video is genuinely good. We optimized for whether the viewer remembers the thing tomorrow. Sketchie’s generator enforces rules drawn from published, peer-reviewed research.

  • Everything draws on, always. Content built up stroke by stroke beats showing completed scenes for both retention and transfer. This is the core mechanism, so we never break it.
  • Six minutes is a cliff, not a guideline. Analysis of 6.9 million online-learning sessions shows engagement near 100% under 6 minutes, roughly half at 9 to 12 minutes, and a fifth past 12. Sketchie caps videos at 6 minutes and chapters anything longer.
  • Every video ends with a question. A retrieval beat: the question appears, the video pauses, then a one-line recap. Making the learner generate the answer improves learning.
  • Pauses are on purpose. After a scene finishes, the narration holds before the cut. Processing time at boundaries is part of how segmenting improves learning.
  • No decoration. Every visual element on screen is referenced by the narration. Our eval harness treats interesting-but-extraneous content as a failure, not flair.

Read the full spec we built from the research

Pricing

Four plans. Start free with 2 videos.

Solo
$9.99 /mo
40 minutes / month
  • 40 rendered minutes every month
  • Scene editor, all voices, all aspects
  • First 2 videos free to start
See full pricing
Plus
$19.99 /mo
100 minutes / month
  • 100 rendered minutes every month
  • Scene editor, all voices, all aspects
  • API + MCP access at 1x
See full pricing
Most popular
Pro
$49.99 /mo
300 minutes / month
  • 300 rendered minutes every month
  • Scene editor, all voices, all aspects
  • API + MCP access at 1x
See full pricing

Business adds custom branding. Annual billing takes 40% off. See all four plans.

Questions

The honest FAQ.

How do the free videos work?
Sign up and make 2 free videos, up to 1 minute each, with no card required. They carry a small watermark, and you get the full product including the scene editor. Editing does not use up one of your 2 free videos, and your first edit of a video is free. When you are ready for more, pick a plan.
How fast is it?
Under a minute for a full video. That includes the script, the drawings, the narration, and the word-level timing between them. When you edit, a single scene re-renders in seconds.
How much does it cost?
Plans start at $9.99 a month for 40 minutes of rendered video. For scale: a freelance animator or agency typically charges $100 to $900 for one explainer video and takes weeks to deliver it. Full plans on the pricing page.
Is it free to try?
Yes. Your first 2 videos are free, no card required, with the full product including the scene editor. After that, you pick a plan. Your plan starts when you’ve seen it work.
What can I feed it?
A plain prompt, PDF, Word, PowerPoint, TXT, or Markdown. Product docs, lesson notes, SOPs, PRDs, changelogs.
What voices are available?
Choose from 30 curated voices — male and female, warm to crisp. Every voice works across all 79 languages, and you can preview each one before generating.
How long can videos be?
Up to 6 minutes per video, in 30-second steps, or auto length. Longer material becomes a chaptered series. That is a deliberate design decision backed by engagement data, not a limitation we are working around.
Is there an API?
Yes, plus an MCP server for AI agents. API access is included on every paid plan, and API generations draw from your plan minutes at 1x, the same as the app. The POST queues your render and returns its ID. Poll the record or listen to the live SSE status stream. When it is ready, the record contains the video URL and full scene graph, with edits available through the API.
Who is behind this?
A small team building from Lima, Peru. No venture funding.
Sketchie mascot

Your next explainer takes
under a minute.

Get Started
Your first 2 videos are free, up to 1 minute each, watermarked. No card required. Full product, scene editor included.