The OCR API provides advanced capabilities for image analysis and text recognition across a diverse array of sources, encompassing printed materials and manuscripts. Boasting support for hundreds of languages, this potent tool facilitates precise and efficient text recognition, catering to a wide range of applications.

Acquiring the key through Rapid API

Step 1. Logging in to Rapid API

To begin, navigate to the login page of Rapid API at https://rapidapi.com/auth/login and enter your account credentials.

If you are a first-time user of Rapid API, it will prompt you to provide some information about yourself.

Step 2. Subscribing to OCR API

Next, visit the OCR API pricing page at https://rapidapi.com/api4ai-api4ai-default/api/ocr43/pricing. Choose the subscription plan that best suits your requirements.

Once you have selected a plan, click on the subscribe button. You will receive a confirmation message stating “Subscription Created Successfully.”

Step 3. Retrieving the API Key from the Dashboard

Access your Rapid API dashboard by either clicking on “Manage And View Usage” under your subscribed plan or visiting https://rapidapi.com/developer/dashboard.

Expand one of your applications within the dashboard and click on the “Authorization” tab.

You will find a list of authorization keys. Simply copy one of them, and voilà! You now have your OCR API key.

Step 4. Test API

To evaluate the functionality of the API, execute the provided Python code snippet.
It is important to remember to replace API_KEY with your actual API key before running the code.

import sys

import requests
from requests.adapters import Retry, HTTPAdapter

API_URL = 'https://ocr43.p.rapidapi.com'
API_KEY = 'YOUR_RAPIDAPI_KEY'  # Place your API key here

if __name__ == '__main__':
    # We strongly recommend you use exponential backoff.
    error_statuses = (408, 409, 429, 500, 502, 503, 504)
    s = requests.Session()
    retries = Retry(backoff_factor=1.5, status_forcelist=error_statuses)

    s.mount('https://', HTTPAdapter(max_retries=retries))

    url = f'{API_URL}/v1/results'
    with open('img.jpg', 'rb') as f:
        api_res = s.post(url, headers={'X-RapidAPI-Key': API_KEY},
                         files={'image': f}, timeout=20)
    api_res_json = api_res.json()

    # Handle processing failure.
    if (api_res.status_code != 200 or
            api_res_json['results'][0]['status']['code'] == 'failure'):
        print('Image processing failed.')
        sys.exit(1)

    # Parse response and print recognized text.
    text = api_res_json['results'][0]['entities'][0]['objects'][0]['entities'][0]['text']
    print(f'? Recognized text:\n{text}')

More code examples

Our repository with code example have more example for different languages.
Visit it at https://gitlab.com/api4ai/examples/ocr or proceed to code examples using direct links:

• Bash
• C#
• JavaScript
• NodeJS
• PHP
• Python
• Swift

Conclusion

With its unmatched capacity to swiftly transform printed publications into digital formats, accelerate election and poll analyses, and fulfill various other functions, the OCR API stands as an indispensable solution. Employ this potent tool to automate and precisely extract text from images in virtually any language required.