Image to Text OCR: Bulk Screenshot & Scan Reader

Extract text from thousands of images in one run: screenshots, scanned documents, photos of pages, receipts, signs, memes, UI captures. Powered by Tesseract OCR, running inside your Apify run, so your images are never sent to a third-party OCR API.

• Full text per image, line by line
• Confidence score per image (and per word) so you can filter bad reads
• Word bounding boxes (optional): text + pixel position for every word
• 7 languages: English, French, German, Spanish, Italian, Portuguese, Dutch, and mixes like eng+fra
• Layout modes for documents vs. sparse text (screenshots, signs)
• Auto-rotation of phone photos (EXIF)
• Fair pricing: you pay only for images that were read. Broken links cost nothing.

How to use

1. Paste image links into Image URLs (or upload a text file with one URL per line).
2. Choose the language. Pick Sparse text for screenshots and signs.
3. Click Start, then export the results as JSON, CSV or Excel, or fetch them through the API.

Input example

{
  "imageUrls": [{ "url": "https://example.com/scan.png" }],
  "language": "eng",
  "includeWordBoxes": false
}

Output example

{
  "url": "https://example.com/scan.png",
  "status": "ok",
  "text": "INVOICE #4521\nDate: 2026-03-02\nTotal: 149.00 EUR",
  "meanConfidence": 91.4,
  "wordCount": 7,
  "imageWidth": 1240,
  "imageHeight": 1754
}

With Include word bounding boxes on, each item also has words: [{ "text", "confidence", "left", "top", "width", "height", "block", "line" }].

Pricing

Event	Price
Image read	$0.0015 per image

1,000 images cost $1.50. Set a maximum cost per run and the Actor stops cleanly when it is reached.

Need PDFs?

For PDF files (text PDFs and scanned PDFs, with tables), use the companion Actor PDF to Markdown Converter (Tables + OCR).

Limits

• Max 30 MB per image, 2 minutes per image.
• Handwriting is read poorly (Tesseract is built for printed text).
• Very low-resolution images (under ~20 px text height) give low confidence. Check meanConfidence.

Free browser version

Converting just one file? Use the free in-browser converter at hackthehydra.com: no upload, no account.

More ways to use it

• REST API without an Apify account: the same converters are available on RapidAPI as the Document to Markdown API (PDF, DOCX, PPTX, XLSX, images; free plan included).
• Free in your browser: hackthehydra.com has no-upload converters for PDF, Word, Excel, PowerPoint and images.

Use cases

• Research and archives: digitise scans, screenshots and photographed documents in bulk.
• LLM pipelines: feed text from images into RAG or classification steps.
• Ops: read receipts, labels and slides at scale instead of retyping them.

Integrations

Python (Apify client):

from apify_client import ApifyClient

client = ApifyClient("<APIFY_TOKEN>")
run = client.actor("extas_corp/image-ocr").call(run_input={"imageUrls": [{"url": "https://raw.githubusercontent.com/tesseract-ocr/tessdoc/main/images/eurotext.png"}]})
for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item.get("text"))

Make, Zapier, n8n: add the Apify app, choose Run Actor (or Run Actor and get dataset items), set the Actor to extas_corp/image-ocr and map the JSON input. The same Actor can be started on a schedule from Apify itself, with a webhook to your own endpoint when the run finishes.

FAQ

Which languages? Any Tesseract language code, set with the language input (default eng).

How accurate is it? Good on clean, high-resolution images; low-resolution or handwritten input gives weaker results.

Do I need to pay to try it? New Apify accounts include free monthly platform credit (about $5 on the free plan at the time of writing), so you can run the example input above and many more items before paying anything. You only pay the per-event price listed under Pricing; runs that return nothing or fail are not charged for the failed items.