PDF, Image & Office to Text/Markdown with OCR
Pricing
from $0.70 / 1,000 page (text layer or office)s
PDF, Image & Office to Text/Markdown with OCR
Input links to PDF, scanned PDF, image, DOCX, PPTX or XLSX files (Google Drive and Dropbox links work). Output one item per document: clean text, LLM-ready Markdown with tables, per-page content, optional RAG chunks. OCR in 24 languages only where needed.
Pricing
from $0.70 / 1,000 page (text layer or office)s
Rating
0.0
(0)
Developer
Ernesto Privato
Maintained by CommunityActor stats
0
Bookmarked
2
Total users
1
Monthly active users
21 days ago
Last modified
Categories
Features
Share
PDF, Image & Office to Text and Markdown (with OCR)
Turn any document into clean text and LLM-ready Markdown in one Actor: PDFs (digital or scanned), images, Word (.docx), PowerPoint (.pptx) and Excel (.xlsx). Tables become Markdown tables and structured rows, scanned pages are read with OCR in 24 languages, and you can get RAG-ready chunks directly.
Why this Actor
- One Actor for every format: PDF, PNG, JPG, TIFF (multi-page), WebP, BMP, GIF, DOCX, PPTX, XLSX. No need to chain a PDF parser, an OCR tool and an Office converter.
- Smart OCR, cheaper runs: in Auto mode the PDF text layer is used when it exists and OCR runs only on scanned pages. You pay the OCR price only for pages that need it.
- Markdown with structure: headings and lists from Word, slide titles and speaker notes from PowerPoint, one table per Excel sheet, and real tables from PDFs placed where they appear on the page.
- RAG-ready: set a chunk size and get the Markdown split on paragraph boundaries.
- Google Drive and Dropbox links work as they are (share links are converted to direct downloads).
- No start fee: you pay per page actually processed. A broken or missing file is not charged and does not stop the run.
Use cases
- RAG and AI agents: feed PDFs, decks and spreadsheets to your LLM as Markdown chunks
- Document processing: invoices, contracts, reports, forms and scans to searchable text
- Data extraction: tables from PDF reports and Excel files as rows of cells
- Archives: OCR of scanned books, letters and faxes in 24 languages
Input example
{"documents": ["https://arxiv.org/pdf/1706.03762","https://example.com/scanned-invoice.pdf","https://drive.google.com/file/d/FILE_ID/view","https://example.com/quarterly-report.docx"],"ocrMode": "auto","ocrLanguages": ["eng", "deu"],"chunkSize": 2000}
Output example
One item per document:
{"url": "https://example.com/quarterly-report.docx","fileName": "quarterly-report.docx","fileType": "docx","pageCount": 1,"pagesProcessed": 1,"ocrPages": 0,"truncated": false,"text": "Quarterly report\nRevenue grew 12% year over year.\n…","markdown": "# Quarterly report\n\nRevenue grew 12% year over year.\n\n| Quarter | Revenue |\n|---|---|\n| Q1 | 100 |\n| Q2 | 112 |","wordCount": 18,"tableCount": 1,"chunks": ["# Quarterly report\n\nRevenue grew 12%…"],"pages": [{ "page": 1, "text": "…", "markdown": "…", "tables": [[["Quarter", "Revenue"], ["Q1", "100"], ["Q2", "112"]]], "ocr": false }],"error": null}
What a "page" is: a PDF page, an image (or a TIFF frame), a PowerPoint slide, an Excel sheet; a Word document counts as one page.
Options
- OCR: Auto (only scanned pages), Always (every PDF page, e.g. PDFs with a broken text layer), Never (text layer only)
- OCR languages: English, German, French, Italian, Spanish, Portuguese, Dutch, Polish, Swedish, Danish, Norwegian, Finnish, Czech, Romanian, Hungarian, Turkish, Russian, Ukrainian, Greek, Chinese (simplified), Japanese, Korean, Arabic, Hindi
- Pages (e.g.
1-5,8) and max pages per document - Per-page content, tables as data, RAG chunk size, OCR resolution
Pricing
Pay per event, only for results you get:
- $0.001 per page with a text layer, slide, sheet or Word document; $0.004 per page or image that needs OCR. No start fee.
- Apify subscribers pay less: 10% off on Bronze, 20% on Silver, 30% on Gold and higher plans.
- Set a maximum charge per run in the run options: the Actor stops cleanly when it is reached.
Input reference
| Field | Type | Default | Description |
|---|---|---|---|
documents (required) | array | Document URLs. Public links to PDF, image (PNG, JPG, TIFF, WebP, BMP, GIF), Word (.docx), PowerPoint (.pptx) or Excel (.xlsx) files. Google Drive and Dropbox share links work too. | |
ocrMode | string (auto, always, never) | auto | OCR. Auto reads the PDF text layer and runs OCR only on pages without text (scans). Images are always read with OCR. |
ocrLanguages | array of codes | eng | OCR languages. Languages in the scanned documents. Pick only the ones you need: more languages = slower. |
pages | string | Pages. PDF pages to read, e.g. '1-5,8'. Leave empty for all. | |
maxPagesPerDocument | integer | Max pages per document. Stop after this many pages in each document. 0 or empty = no limit. | |
includePages | boolean | true | Include per-page content. Add a 'pages' list with text, Markdown, tables and OCR flag for each page (slide, sheet). |
includeTables | boolean | true | Include tables as data. Add the tables found on each page as rows of cells (they are always in the Markdown). |
chunkSize | integer | RAG chunk size (characters). Also split the Markdown into chunks of at most this many characters, on paragraph boundaries (e.g. 2000). 0 or empty = no chunks. | |
ocrDpi | integer | 200 | OCR resolution (DPI). Resolution used to render scanned PDF pages for OCR. 300 for small print, 200 is faster. |
Tips
- Files must be reachable by a public link. To use a file from your computer, upload it to an Apify key-value store, Google Drive or Dropbox and paste the link.
- For scans, choose only the languages that are in the document: OCR is faster and more accurate.
- Password-protected PDFs cannot be read.
Privacy
Documents are downloaded, processed in memory during the run and returned only to your dataset: they are not stored or shared elsewhere. When a paying customer's run ends, the developer receives an anonymous notification with only numbers (results returned, amount charged, duration). Your input, the documents and your identity are never sent.