GetSearchablePDF

By Superdocs

Get New App Alerts

Open in ChatGPT

Open in Claude

Overview

Attach a scanned PDF or a photo of a document and GetSearchablePDF adds an OCR text layer, so you can search, select and copy its text. A panel in the chat shows progress and then a Download button for each file, up to 10 at a time. Only the pages without text go to OCR; pages that already have text are left as they are. If an old scan has a wrong text layer, run OCR anyway to replace it. Sign in with your GetSearchablePDF account to use it. Files are deleted after 60 minutes and never used for training.

Tools

searchable_pdf_convert

ChatGPT

Makes scanned PDFs or images (PNG, JPEG) searchable with OCR, so their text can be selected, copied and searched. Takes up to 10 attached files in files, or the job_ids of files uploaded with searchable_pdf_prepare_upload; with neither, the panel shows a file picker. Shows one panel with progress and a download button for each file. Each conversion creates a new PDF; the uploaded files are not changed. With force_ocr, the new PDF's text comes from OCR on every page instead of from the file's existing text.

searchable_pdf_convert_rest

ChatGPT

Converts the pages of an earlier conversion that were skipped because the page balance ran out (skipped_pages), and returns the completed file. Only those pages use pages from the balance.

searchable_pdf_jobs

ChatGPT

Returns the status of the conversions shown in the GetSearchablePDF panel. The panel uses it to refresh its rows.

searchable_pdf_pages_left

ChatGPT

Returns how many pages are left in the user's GetSearchablePDF account, the largest file size and page count their plan allows, and a link to a page that describes pages and plans.

searchable_pdf_prepare_upload

ChatGPT

Returns a one-time HTTPS upload URL and headers for sending one file's raw bytes from a code-execution sandbox. A successful upload returns a job_id that searchable_pdf_convert accepts.

searchable_pdf_redo_with_ocr

ChatGPT

Creates a new searchable PDF from the file of an earlier conversion, with OCR on every page, so the new PDF's text comes only from OCR. The original file and the earlier result are not changed. Each page uses one page from the balance.