What does the OCR API do?

<p>After uploading a document as POST to the OCR API, scanned paper documents, PDF files or digital images are converted to editable and searchable PDF files. For this purpose, the text recognized with OCR is placed as HOCR as an overlay over each page of the document.</p>

What are the costs of using the OCR API?

<p>The cost of using the OCR API can range from €0.002778 to €0.15 per page, depending on subscription plan.</p>

Does the OCR API offer any functions other than OCR?

Yes, it can be set to rotate pages automatically. In addition, the OCR API can automatically convert formats such as PowerPoint, Excel, emails or Word into a PDF documents that are archiveable. Furthermore, when uploading PDFs that are partially broken, algorithms are applied to repair this PDF file automatically.

OCR API for your software

Using deep vision OCR the text from an image or a scanned document is read and returned as JSON and PDF. This means more than 100 languages can be read from nearly any kind of business document, like a scan of a non digital document or an image. Besides other document APIs the cloud hosting is readily available for processing and can be tested for free.

Free Online OCR API

Create your own project now for free via API for automated text recognition and data extraction of your documents and images.

API Docs Python SDK Prices for power users

By loading the video, you accept YouTube's privacy policy.
Learn more

Load video

Always unlock YouTube

Online OCR API

The Konfuzio OCR software gives you intelligent text recognition for 70+ languages and a digital Extraction of all relevant information from the respective text. This also applies to text entered by hand in applications and documents. The video shows you all the functionalities of our API.

OCR integration via REST API

Using the vision OCR achieves impressive results when processing files to read text data from image based documents like scans in various languages. Processing images or documents via our cloud hosted APIs provides instant access to the vision AI to extract text data. More APIs for processing documents with vision or natural language AI can be found in our Swagger documentation.

To the API

Python OCR SDK

Our Python OCR SDK is fully documented to process documents on your systems. Create applications yourself that extract textual information from images and documents. The Python SDK gives you all the functionality of the REST API in your Python code.

More about Python OCR SDK

OCR Web API for PDF, JPG, TIF and EML documents

Thanks to Konfuzio vision OCR API you can convert your images and PDF documents into searchable files in PDF or PDF/A format for free. On request, the text can also be processed into other file formats (e.g. DOCX, XLSX, PPTX).

Read supported file types

From PDF to JSON with Vision OCR

Get your OCR output as JSON format. On request, Konfuzio can also export your extracted data in a structured CSV format.