Overview

Our OCR API is the ultimate solution for text recognition from handwritten documents and scanned images. Our cutting-edge technology can process all languages on the planet with amazing accuracy, making it idea for international businesses and organizations. With low latency and high availability, this API guarantees fast and reliable results every time. Whether you need to extract text from a scanned document for archiving purposes or recognize text from handwritten notes for digital storage, our OCR API has you covered.

Main Features

• Text Recognition from image: Accurately extract text from images using advanced OCR technology.
• Text Recognition from pdf: Accurately extract text from PDF documents using advanced OCR technology.

---

Endpoints

HTTP Method	URL	Description
POST	https://ocr-wizard.p.rapidapi.com/ocr	Extract Text from image
POST	https://ocr-wizard.p.rapidapi.com/ocr-pdf	Extract Text from PDF

---

Text Recognition from image

Endpoint Descriptions

Proprity	Description
URL	https://ocr-wizard.p.rapidapi.com/ocr
Methode	POST
POST Parameters	image: BINARY OR url: STRING
Supported content-type	application/x-www-form-urlencoded | multipart/form-data

---

Parameters Descriptions

Field	Type	Required	Description
image OR url	BINARY OR STRING	YES	The image to be processed by the OCR API.

---

Response Schema

"responses": {
  "statusCode": ...,
  "body": {
    "fullText": ...,
    "detectedLanguage": ...
    "annotations": [
      {
        "text": ...
	"boundingPoly":
      }
    ]
  }
}

Response Field Descriptions

Field	Type	Description
statusCode	int	Status code of image processing.
body.fullText	string	The full text extracted from the image.
body.detectedLanguage	string	The detected language of the text.
body.annotations[]	array	A list of annotations, each item correspond to one detected word.
body.annotations[].text	string	detected word.
body.annotations[].boundingPoly[]	array	The boundingPoly around the detected word, represented in the following format [left_top_point, right_top_point, right_bottom_point, left_bottom_point].

---

Text Recognition from pdf

Endpoint Descriptions

Proprity	Description
URL	https://ocr-wizard.p.rapidapi.com/ocr-pdf
Methode	POST
POST Parameters	pdf_file: BINARY | first_page: INTEGER | last_page: INTEGER
Supported content-type	application/x-www-form-urlencoded | multipart/form-data

---

Parameters Descriptions

Field	Type	Required	Description
pdf_file	BINARY	YES	The pdf to be processed by the OCR API.
first_page	INTEGER	NO	The first pdf page to be processed, default is 1.
last_page	INTEGER	NO	The last pdf page to be processed, default is 1.

---

Response Schema

"responses": {
  "statusCode": ...,
  "body": {
    "pages": [
      "fullText": ...,
      "detectedLanguage": ...
      "annotations": [
        {
          "text": ...
	  "boundingPoly":
        }
      ]
    ]
  }
}

Response Field Descriptions

Field	Type	Description
statusCode	int	Status code of pdf processing.
body.pages[]	array	A list of processed PDF page results, with each item corresponding to one page.
body.pages[].fullText	string	The full text extracted from the pdf page.
body.pages[].detectedLanguage	string	The detected language of the text.
body.pages[].annotations[]	array	A list of annotations, each item correspond to one detected word.
body.pages[].annotations[].text	string	detected word.
body.pages[].annotations[].boundingPoly[]	array	The boundingPoly around the detected word, represented in the following format [left_top_point, right_top_point, right_bottom_point, left_bottom_point].

---

Examples:

Example 1 : Handwritten Text:

• Image url : https://openmediadata.s3.eu-west-3.amazonaws.com/pexels-monstera-5709059.jpg
• Results:

Example 2 : German Text

• Image url : https://openmediadata.s3.eu-west-3.amazonaws.com/deutsch_text.png
• Results:

Example 3 : English Text

• Image url : https://openmediadata.s3.eu-west-3.amazonaws.com/english_text.png
• Results:

Example 4 : Arabic Text

• Image url : https://openmediadata.s3.eu-west-3.amazonaws.com/arabic_text.png
• Results: