Wiro - Easy Ocr icon

Wiro - Easy Ocr

EasyOCR is the text-recognition model that identifies and extracts text from images

Wiro - Easy Ocr

AI-generated

Overview

This node integrates with the Wiro Easy OCR API to perform optical character recognition (OCR) on an input image URL. It sends the image URL and selected languages to the API, waits for the OCR task to complete via polling, and returns the OCR task status and result URL. This node is useful for extracting text from images in automation workflows, such as processing scanned documents, receipts, or any image containing text.

Use Case Examples

  1. Extract text from a scanned document image by providing its URL and specifying the language(s) for OCR.
  2. Automate text extraction from receipts or invoices by inputting their image URLs and retrieving the recognized text results.

Properties

Name Meaning
Input Image URL The URL of the image from which text will be extracted.
Language One or more languages to be used by the OCR engine for text recognition.

Output

JSON

  • taskid - The unique identifier of the OCR task.
  • url - The URL where the OCR result can be accessed.
  • status - The status of the OCR task, indicating if it completed successfully or failed.

Dependencies

  • Wiro API key and secret credentials for authentication

Troubleshooting

  • If the node throws an error about missing or invalid task ID or socket access token, verify that the Wiro API credentials are correct and the API endpoint is reachable.
  • Polling may fail or timeout if the OCR task takes too long or the socket access token is invalid; ensure network connectivity and valid credentials.

Discussion