Amazon Textract

By Amazon Web Services ยท Document processing and OCR

About Amazon Textract

AWS service that extracts text, tables, forms and query answers from scanned documents through an API.

Amazon Textract is a machine learning service from AWS that reads text, tables and form fields from scanned documents and images. Developers call it through an API, and it returns the text along with the structure of the page, such as which value belongs to which form label.

It also has specialized features for invoices and receipts, identity documents and lending paperwork, and a queries option where you ask for a specific field in plain language. Because it is a building block, teams usually pair it with their own review step and storage.

It suits companies that already run on AWS and have developers to build the workflow. Check which AWS region processes your documents, how results are stored, and how you will route low-confidence fields to a person.

Details

  • Developer API

    Yes

Not enough info yet on free plan or free tier, mobile app, single sign-on (SSO), choice of data region. Check the tool's own site.

Listing written by MyCloudDMS, checked 2026-11-03. Report a correction or request removal. Back to document processing and ocr.