WorkStudio Help
DocStudio

Use OCR for Scanned PDFs

Last change: Not recorded

Run OCR on scanned PDF pages so DocStudio can summarize or extract actions from documents that do not contain selectable text.

Some PDFs already contain text. Others are scanned images.

DocStudio first checks whether text can be extracted directly. If the PDF looks scanned, the Summary and Actions / Tasks windows offer OCR.

The OCR flow is:

  1. Open AI Summary or AI Actions / Tasks for the PDF document object.
  1. Choose OCR Language.
  1. Choose OCR Pages, such as 1, 1-3, or 2,5-6.
  1. Review the estimated credits and estimated duration.
  1. Click Run OCR.

OCR text is saved on the document object. Summary and Actions / Tasks can reuse it later without extracting the PDF again.

Refresh OCR runs OCR again and replaces the saved OCR text. Use it when you change the OCR language, change the page range, replace the source document, or want to retry a poor OCR result.

OCR is a preparation step. After OCR finishes, run Summary or Actions / Tasks on the saved text.

Related: Summarize Attached Documents with AI, Extract Actions and Tasks from Documents, Attach Documents to a DocStudio File.

Open DocStudio ↗

Run OCR

Choose OCR language, page range, review the estimate, and run OCR before generating AI Summary or Actions.

AI Summary modal showing the Run OCR action for a scanned PDF.

Refresh OCR

Use Refresh OCR when you change language, change pages, replace the source document, or want to retry a poor OCR result.

AI Summary modal showing the Refresh OCR action.

OCR result available

Once OCR is saved, the document source can show OCR, Summary, and Actions badges.

Documents In This File list with summary and actions available.

Enable JavaScript to use reading progress and usefulness ratings.