# Extract text from a batch of images for search

**Use case:** 

Read a list of public image URLs with OCR and keep only the full text and counts, small rows for a search index or an LLM that needs the words and not their positions.

## Input

```json
{
  "image_urls": [
    "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/testocr.png",
    "https://raw.githubusercontent.com/naptha/tesseract.js/master/tests/assets/images/cosmic.png"
  ],
  "language": "en",
  "base64Images": [],
  "keyValueStoreRecords": [],
  "outputDetail": "text",
  "translateTo": "en",
  "maxItems": 100,
  "maxMegabytesPerImage": 40
}
```

## Output

```json
{
  "image_url": {
    "label": "Image URL",
    "format": "string"
  },
  "image_source": {
    "label": "Image Source",
    "format": "string"
  },
  "full_text": {
    "label": "Full Text",
    "format": "string"
  },
  "paragraphs": {
    "label": "Paragraphs",
    "format": "array"
  },
  "word_count": {
    "label": "Word Count",
    "format": "number"
  },
  "mean_confidence": {
    "label": "Mean Confidence",
    "format": "number"
  },
  "image_width": {
    "label": "Image Width",
    "format": "number"
  },
  "image_height": {
    "label": "Image Height",
    "format": "number"
  },
  "words": {
    "label": "Words",
    "format": "array"
  },
  "language": {
    "label": "Language",
    "format": "string"
  },
  "detected_language": {
    "label": "Detected Language",
    "format": "string"
  },
  "ocr_engine": {
    "label": "OCR Engine",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [OCR Image to Text API: Words, Boxes, Confidence](https://apify.com/pradio/image-text.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/pradio/image-text.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

This Task's input is already configured above. Use it as-is rather than inventing a new one.

Do not guess an integration path. Every one of them is in the agent quickstart at https://apify.com/agents.md: the Apify MCP server, Agent Skills with the Apify CLI, the JavaScript and Python clients, the REST API, and the account-free path for an agent with no human to sign in. It also carries the rule on stating cost before the first paid run.

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/pradio/image-text.md

Each client library has reference documentation the quickstart does not restate: [JavaScript/TypeScript](https://docs.apify.com/api/client/js/docs.md) (`npm install apify-client`) and [Python](https://docs.apify.com/api/client/python/docs.md) (`pip install apify-client`).