Explainer editor help
The explainer turns an idea, a text or your voice into an animated video. You keep the final say: every AI action is explained in one sentence and can be undone.
5 tips inside the editor, skippable at any time.
Your first video in 3 steps
- Pick a style (each thumbnail shows how it renders), then write your topic in one sentence and click “Write with AI”. No idea yet? “Use a template” opens the style's demo, “Try with an example” spends no AI budget.
- Review the scenes: click an element to move it, change a word of the narration, or ask the Director for a tweak.
- Start the render (⌘↵): the MP4 shows up in your list, ready to download.
AI writing and rendering come with every subscription, from Starter up. On the Free plan you can browse styles, open a template and the example.
Keyboard shortcuts
In the editor, “?” opens this list. Single-key shortcuts don't fire while typing and can be turned off in that same window.
| ⌘Z / Ctrl+Z | Undo |
|---|---|
| ⇧⌘Z / Ctrl+Y | Redo |
| ⌘D | Duplicate element or scene |
| ⌘↵ | Start the render |
| ⌫ / Del | Delete selection (undoable) |
| ← ↑ → ↓ | Move element (Shift: ×10) |
| Alt + ← → | Reorder scenes / layers |
| [ ] | Previous / next scene |
| , . | −/+ 0.1 s in the preview |
| Space | Play / pause the scene |
| / | Search the library |
| Esc | Deselect / close |
| ⌘K | Open / close the Director |
| C | Comment here (current scene, playhead) |
| ? | Open the shortcut list |
| Space (hold) | Talk to the Director while its panel is open |
Conceptos
- Scene
A scene is one narration sentence and the elements that illustrate it. The video is the sequence of your scenes in the timeline.
- Element and library
An element is an animated drawing (2D pixel art or 3D object) placed in a scene. The library holds thousands of them, filed by theme and searchable by meaning (“/”).
- Director
The Director is a copilot you talk to (“make scene 3 more dramatic”). It proposes script changes, shown as a diff before they apply.
- Polish (critique)
Polish makes the AI review its own frames: overlaps, empty areas, off-topic elements. Each scene gets a score and suggested fixes.
- Forged elements
When an element is missing, Claude draws it from your description, renders it and reviews it. It goes to “My elements”, private, and you can propose it for publication.
- Narrate and imported audio
Narrate into the mic (one or more takes) or import an audio file: the narration is transcribed word by word and the video builds on your voice. You can re-record a single sentence.
- Variants
“3 variants” proposes three takes on a scene, side by side, with their cost shown before you start. You choose instead of building.
- Versions (history)
Every generation, accepted proposal, Polish and import adds a version, with a thumbnail and a readable diff. You can compare two versions and go back to one.
- Taste
The AI remembers your choices (accepted or declined proposals, elements kept or discarded, pacing) and applies them to the next videos. The “What the AI knows about my taste” page shows everything it keeps.
- Brand
The brand kit (logo, colors, font, tone, intro and outro, watermark) is applied by the engine to every render. Set it in Settings > My brand.
- Templates
A template is a reusable script with parameters such as {{sujet}}. “Fixed” fills the parameters without AI; “Recompose” lets the AI rewrite from the template.
- Agentes
An external agent (Claude Code, Claude Desktop, a script) can produce a video end to end through MCP or the API, with a key scoped “read” or “production”. Produced videos carry the key's name in your list.
Connect your agent
- Create a key in Settings > Integrations: “read” to look, “production” to produce. The secret is shown only once.
- Plug in the MCP server (claude mcp add … /mcp with the Authorization header) or call POST /api/agent/produce.
- Always start with dry_run: estimated cost, nothing billed. Follow the production (SSE or signed webhook) and cancel it if needed.
Create an API key · Interactive API reference · llms-api.txt
Step-by-step guide with real outputs (MCP, dry_run, signed webhook): docs/agents.md.