OCR Image
The OCR Image block extracts text from an image by accepting a URL pointing to the image file.
Extract text from images using OCR
The OCR Image block extracts text from an image by accepting a URL pointing to the image file. It processes the image and returns the recognized text as a string output, making the content of the image available for further use in a workflow. The single required input is imageUrl, a string containing the URL of the image to be analyzed.
The block produces one output variable containing the extracted text from the image. This text can then be passed to other blocks in a workflow for tasks such as parsing, classification, storage, or further AI analysis. The block handles the full extraction process internally, so no additional configuration is needed beyond providing the image URL.
This block fits into workflows that need to process image-based documents, forms, screenshots, or any visual content containing readable text. It is commonly used as an early step in pipelines where downstream logic depends on the textual content of an image rather than the image itself.
What you can build
Real-world workflows powered by the OCR Image block.
Invoice Data Extraction
Extract text from scanned invoice images to capture line items, totals, and vendor details for automated processing.
Form Digitization
Convert handwritten or printed form submissions into machine-readable text for storage in a database or CRM.
Receipt Parsing
Pull text from receipt images uploaded by users to identify purchase amounts, dates, and merchant names.
Screenshot Content Analysis
Extract text from screenshots to enable search, moderation, or classification of content captured in image format.
ID Document Reading
Read text fields from images of identification documents to support verification or onboarding workflows.
Printed Label Processing
Extract product names, barcodes, or instructions from images of physical labels for inventory or compliance workflows.
Ready to add OCR Image to your workflow?
Get Started FreeCommon questions about OCR Image
What input does the OCR Image block require?
The block requires a single input: imageUrl, which is a string containing the URL of the image you want to extract text from.
What does the OCR Image block return?
The block returns one output variable containing the extracted text from the provided image as a string.
What kinds of workflows commonly use this block?
This block is commonly used in workflows that process scanned documents, uploaded images, screenshots, or any visual content where the text needs to be read and passed to downstream steps for parsing, analysis, or storage.
Does the image need to be hosted at a publicly accessible URL?
The block accepts an imageUrl string as its input, so the image must be accessible via a URL at the time the block runs.
Can the extracted text be used by other blocks in the same workflow?
Yes. The output variable containing the extracted text is available to downstream blocks in the workflow, allowing it to be passed into AI analysis, text parsing, database storage, or other processing steps.
Related capabilities
Transcribe Audio
Convert an audio file to text using a transcription model.
Analyze Image
Analyze an image using a vision model based on a text prompt.
Analyze Video
Analyze a video using a video analysis model based on a text prompt.
Deep Research
Sourced information from the web
Analyze CSV
Analyze CSV with code
Add OCR Image to your workflow
Build powerful AI workflows with drag-and-drop blocks. No coding required.