Image-to-text API for OCR and text extraction workflows

Use Nutrient DWS to extract text from images when the workflow needs OCR-style text output instead of static image files. Start with a cloud image-to-text API built for scanned documents, receipts, forms, and document-understanding workflows.

Extract text from images

Use an image-to-text API when the workflow needs OCR-style text output from receipts, scans, forms, screenshots, and other image-based documents.

Built for API-driven OCR workflows

Use REST, Postman, JavaScript, Python, Java, C#, PHP, or HTTP to automate image-to-text extraction inside search, compliance, and document processing systems.

Fast path from evaluation to implementation

Connect image-to-text extraction to getting started, pricing, and the broader data extraction hub so teams can validate the right OCR and text-output path quickly.

Try it out

This example extracts text from an uploaded image file.


Try it out in three steps

  1. Add an image named document.png to your project folder.
  2. Run the code from the same folder.
  3. Open result.json to inspect the extracted text output.
curl -X POST https://api.nutrient.io/build \
-H "Authorization: Bearer your_api_key_here" \
-o result.json \
--fail \
-F page=@page1.jpg \
-F instructions='{
"parts": [
{
"file": "page"
}
],
"output": {
"type": "json-content",
"plainText": true,
"structuredText": true
}
}'

Data Extraction API

Extract specific fields from any document

Define a schema and get back typed JSON with confidence scores and source context for every value.

Start free:

    • 5,000 credits per month
    • No credit card required
    • Schema generator in Studio

Security is our top priority

SOC 2 Type 2 audited

Nutrient’s infrastructure is SOC 2 Type 2 audited and GDPR-compliant. See our privacy policy and security documentation for details on data handling.

HTTPS encryption

All communication between your application and Nutrient is done via HTTPS to ensure your data is encrypted when it’s sent to us.

Safe payment processing

All payments are handled by Paddle. Nutrient DWS Processor API never has direct access to any of your payment data.

Frequently asked questions

What is an image-to-text API?

An image-to-text API lets you extract text from images using optical character recognition (OCR) with a single API call. Nutrient’s DWS Processor API extracts text from receipts, scans, forms, and screenshots without building your own document processing infrastructure.

How do I extract text from an image programmatically?

Send a request to the Nutrient DWS Processor API with your image file and receive the extracted text in the response. You can call it via REST, Postman, curl, JavaScript, Python, Java, C#, PHP, or plain HTTP.

What image formats does the image-to-text API support?

The API supports common image formats such as JPEG and PNG, as well as PDF — so you can extract text from scanned documents, screenshots, and multipage files.

Is there a free image-to-text API?

Yes. Sign up to receive processing credits and try image-to-text extraction before choosing a Processor API plan.

Are there rate limits on the image-to-text API?

Rate limits depend on your Processor API plan. See the Processor API pricing page or REST API reference for throughput and request limits for your tier.

Can I extract text from multiple images in batch?

Yes. The Processor API supports batch workflows, so you can automate text extraction across many documents for search, compliance, and data extraction systems.

Which programming languages are supported?

You can call the API from any language that makes HTTP requests. Nutrient provides examples for JavaScript, Python, Java, C#, and PHP, plus REST and a Postman collection.

Ready to try it?

Create an account to get your DWS Processor API key and start making API calls.