DtDoctransform
All tools

OCR Text Extractor

OCRLive API

Read text from scans and images.

Drop a file here or choose

PDF, PNG, JPEG, TIFF, BMP, WEBP

Options

Cost2 / page

Charged per page — total depends on your file.

Free to try Private & secure Deleted after 1 hour

Accepts

PDF, PNG, JPG, TIFF

Returns

Data

Batch

Single file

Cost

2 / page

About OCR Text Extractor

Read text out of scans and photos with a tuned recognition pipeline (deskew, denoise, adaptive thresholding) that reaches ~99% accuracy on clean documents. Get plain text or a searchable PDF.

  • Make scanned contracts searchable
  • Pull text from photographed pages
  • Digitize paper records at scale

How it works

  1. 1

    Upload your file

    Drop in your PDF, Office files, and images, or pick from your device.

  2. 2

    Set your options

    Tune a couple of settings to get exactly the result you want.

  3. 3

    Download the result

    Grab your extracted data right away. Files are deleted automatically after an hour.

Prefer to automate? Call it by API.

curl -X POST https://api.doctransform.io/ocr \
  -H "Authorization: Bearer dt_live_••••" \
  -F "file=@document.pdf" \
  -F "output=text" \
  -F "language=eng"

Questions, answered

Yes — it's free to try in your browser. Programmatic use through the API costs 2 credits per page per run.

They're encrypted in transit, processed only for your request, and automatically deleted within an hour. We never use them to train models.

PDF, Office files, and images.