Image to Text OCR

Extract text from images: paste image links or upload files and get the text back as JSON, CSV or XLSX. It works on screenshots, receipts, scanned pages, photos of documents, labels and signs. It reads PNG, JPEG, WebP, multi-page TIFF, BMP and GIF.

Built for: digitizing receipts and scans, pulling text from screenshots, feeding images into AI and search pipelines, and bulk OCR jobs in Make, Zapier or n8n.

What you get

• Text with confidence. Each image returns its text, keeping lines and paragraphs, plus an overall confidence score from 0 to 100.
• Word positions (optional). Every word with its confidence and pixel box (left, top, width, height) in the original image's coordinates. Useful for highlighting, redaction and form parsing.
• Layout modes. Auto for documents and screenshots, Sparse for signs, labels and product photos, Single block for a cropped paragraph, Single line for codes and plates.
• 7 languages: English, Spanish, French, German, Portuguese, Italian and Dutch, mixable in one run.
• Automatic cleanup. It fixes phone-photo rotation (EXIF), flattens transparent backgrounds, converts to grayscale, boosts contrast and upscales small images before OCR.
• Multi-page TIFF. Each page is read, with per-page text.
• Fair billing. Images with no text, failed downloads and unsupported files are never charged. The run stops cleanly at your maximum cost per run.

How to use

1. Add image links (one per line) or upload images in Images.
2. Pick the Languages that appear in your images.
3. Choose a Text layout: Auto suits most images.
4. Click Start, then download results as JSON, CSV, XLSX or HTML, or fetch them with the API.

curl -X POST "https://api.apify.com/v2/acts/ridgeline_apps~image-to-text-ocr/run-sync-get-dataset-items?token=YOUR_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"files": ["https://example.com/receipt.jpg"], "ocrLanguages": ["eng"]}'

Input

Field	Description	Default
files	Image URLs or uploaded files	required
ocrLanguages	Any of eng, spa, fra, deu, por, ita, nld	["eng"]
layout	auto, sparse, block or line	auto
includeWordBoxes	Add every word with confidence and position	false
maxFileSizeMb	Larger files are skipped (free)	20
maxPagesPerImage	Pages read from multi-page TIFFs	10

Output

{
  "url": "https://example.com/receipt.jpg",
  "fileName": "receipt.jpg",
  "status": "ok",
  "text": "Invoice number 48213 was issued to Ridgeline Supply on March\n4 2026. The total amount due is 1,284.50 dollars...",
  "confidence": 95.7,
  "wordCount": 34,
  "hasText": true,
  "format": "jpeg",
  "width": 1600,
  "height": 700,
  "pageCount": 1
}

With Include word positions on, a pages list includes every word:

{ "text": "48213", "confidence": 96.4, "left": 412, "top": 160, "width": 118, "height": 34 }

Images that can't be read come back with "status": "error" and a plain-English error. They are never charged.

Pricing

Pay per image with text found, with no subscription. Each page of a multi-page TIFF counts as one image. Images with no text and failed images are free. The exact price is shown on the Pricing tab, and you can set a maximum cost per run in the run options.

FAQ

How accurate is it? On clear printed text, such as screenshots, scans and receipts, confidence is usually above 90%. Blurry, angled or low-light photos score lower; the confidence score tells you which results to double-check.

Handwriting? OCR is designed for printed text. Handwriting results are poor.

Animated GIFs? Only the first frame is read.

Where do my images go? Images are downloaded into your own Apify run and processed there with Tesseract. Nothing is sent to any third-party AI or OCR service.

Legal

Only process images you have the right to use. You're responsible for the images you submit and how you use the extracted text. Not intended for medical records (PHI) or other regulated data that requires a signed processing agreement.

Built on open-source software: Tesseract OCR (Apache-2.0), Pillow (MIT-CMU) and httpx (BSD-3-Clause).

Questions or a feature request? Open an issue on the Issues tab.