> ## Documentation Index
> Fetch the complete documentation index at: https://docs.squeditor.com/llms.txt
> Use this file to discover all available pages before exploring further.

# AI

> Configure how editor controls automatically generate copy or images using AI.

Squeditor natively supports interacting with AI models (like Gemini) to assist users in writing content or generating images. By attaching the `ai_config` object to an eligible control, you can define the type of generation, provide boilerplate prompts, and limit boundaries.

You only need to define `ai_config` once per control schema.

<Note>AI generation is currently only supported by three control types: <Badge color="blue">text</Badge>, <Badge color="blue">textarea</Badge>, and <Badge color="blue">media</Badge>.</Note>

## Text / Textarea

Used to instantly generate headlines or body copy.

```json squeditor.json theme={null}
{
  "id": "heading_text",
  "label": "Heading",
  "type": "text",
  "ai_enabled": true,
  "ai_config": {
    "type": "headline",
    "max_length": 40,
    "prompt": "Generate a compelling headline for a SaaS business tool",
    "variations": 3
  }
}
```

<Expandable title="properties" defaultOpen>
  <ParamField path="type" type="string" required>
    The text generation type. Usually `"headline"` for short copy or `"body_text"` for paragraphs.
  </ParamField>

  <ParamField path="max_length" type="number">
    The maximum character length the AI should try to adhere to.
  </ParamField>

  <ParamField path="prompt" type="string">
    The baseline context prompt passed to the AI model. The user can tweak this in Squeditor.
  </ParamField>

  <ParamField path="variations" type="number">
    The number of unique text options the AI should return for the user to pick from.
  </ParamField>
</Expandable>

***

## Media

Used to generate images based on prompts directly into the Canvas.

```json squeditor.json theme={null}
{
  "id": "user_image",
  "label": "Image",
  "type": "media",
  "media_type": "image",
  "ai_enabled": true,
  "ai_config": {
    "type": "image",
    "aspect_ratio": "16:9",
    "prompt": "A modern startup office building...",
    "variations": 4
  }
}
```

<Expandable title="properties" defaultOpen>
  <ParamField path="type" type="string" required>
    Must be `"image"`.
  </ParamField>

  <ParamField path="aspect_ratio" type="string">
    Desired image crop ratio (e.g., `"16:9"`, `"1:1"`, `"4:3"`).
  </ParamField>

  <ParamField path="prompt" type="string">
    Base descriptive prompt for the image generation request.
  </ParamField>

  <ParamField path="variations" type="number">
    The number of unique image alternatives to return.
  </ParamField>
</Expandable>