Pricing

from $1.60 / 1,000 converted documents

Try for free

Go to Apify Store

PDF to Markdown & Document to Markdown - Text Extractor, OCR

Try for free

Document parser and PDF parser for LLMs: convert PDF, Word (DOCX/DOC), PowerPoint, Excel and CSV to clean Markdown text. PDF OCR for scanned files, RAG chunks. URLs, uploads, base64. $2/1,000 docs.

Pricing

from $1.60 / 1,000 converted documents

Rating

0.0

(0)

Developer

Yukai Lin

Actor stats

Bookmarked

Total users

Monthly active users

5 days ago

Last modified

Categories

Developer tools

Automation

Features

Document URLs

urls

Optional

Main input (fill this, or documentFile / base64Documents). Public links to PDF, DOCX, DOC, RTF, PPTX, PPT, XLSX, XLS, CSV, ODT, ODS, ODP or XML files (up to 15 MB each), one per line. Google Drive, Google Docs/Sheets/Slides, Dropbox and OneDrive/SharePoint share links are turned into direct downloads automatically. HTML pages also work. Blank or invalid lines are skipped and listed in the results (not charged).

Type:array

Or upload a file

documentFile

Optional

Upload one PDF, DOCX, DOC, RTF, PPTX, PPT, XLSX, XLS, CSV, ODT, ODS or ODP file (up to 15 MB) instead of, or in addition to, the URLs.

Type:string

Base64 documents (API)

base64Documents

Optional

For API and AI-agent calls: a list of {"fileName": "report.pdf", "data": ""}. The file name's extension tells the converter the format. Up to 15 MB per file.

Type:array

Example:

[
  {
    "fileName": "hello.csv",
    "data": "bmFtZSxjaXR5CkFkYSxMb25kb24K"
  }
]

RAG chunk size (characters)

chunkSize

Optional

If set (e.g. 2000), each document also gets a "chunks" array split at paragraph boundaries. 0 = off.

Type:integer

Minimum:0

Maximum:20000

Default:0

Chunk overlap (characters)

chunkOverlap

Optional

Characters repeated between consecutive chunks.

Type:integer

Minimum:0

Maximum:5000

Default:200

Output rows

outputMode

Optional

"One row per chunk" splits each document (chunk size above, 2,000 if 0) and outputs every chunk as its own row with chunkIndex and headingPath. Charged per document either way. Values: document = One row per document; chunks = One row per chunk (for vector databases and CSV).

Type:string

Default:document

Options:

documentchunks

Parallel documents

maxConcurrency

Optional

How many documents are converted at the same time.

Type:integer

Minimum:1

Maximum:30

Default:10

Plain HTTP requests from

httpVia

Optional

Some sites block requests from data centers. Auto retries from a second network before falling back to a real browser. If both are refused, Auto also tries our second server (Oracle, different IP) before a real browser.

Type:string

Default:auto

Options:

autobackenddirectvm

Proxy (optional)

proxyConfiguration

Optional

Only used for requests sent from Apify's network. Apify proxy usage is billed to your Apify account.

Type:object

Clean up PDF text

pdfCleanup

Optional

For PDFs with a text layer: join words hyphenated at line ends ("repre-sentation"), put back spaces lost between text blocks ("AbstractWe") and rebuild simple number tables as Markdown tables. Each item reports what was changed in "pdfCleanup". Turn off to get the raw converter text.

Type:boolean

Default:true

OCR for scanned PDFs

ocr

Optional

Transcribe PDFs that have no text layer (scans, photos of pages) with an AI vision model, page by page. Tables become Markdown tables; most languages work, including Chinese and Japanese. Costs $0.005 per transcribed page on top of the document price, and only applies to PDFs without extractable text.

Type:boolean

Default:false

OCR: max pages per document

ocrMaxPages

Optional

Only the first pages up to this number are transcribed (a cost cap). The item gets "ocrTruncated": true when the PDF has more pages.

Type:integer

Minimum:1

Maximum:500

Default:20

OCR: document language (optional)

ocrLanguage

Optional

A hint such as "Traditional Chinese", "German" or "Japanese". Leave empty to detect it.

Type:string

Document URLs (request list, optional)

documentUrls

Optional

Same as the list above, in Apify's request-list format (also accepts a link to a text file of URLs). Kept for older inputs; the plain list above is recommended, especially for API calls.

Type:array

Audio Transcription - Speech to Text, Audio to Text, Whisper

tidytools/audio-transcriber

Speech to text for audio, video, YouTube and podcast RSS, using Whisper. Get text with timestamps plus SRT, VTT, TXT and Markdown files. $0.006 per started audio minute; optional speaker labels $0.015/min. Failed and silent files are free. Up to 1,000 links per run.

Yukai Lin

235

AI Web Scraper - Extract Structured Data & URL to JSON

tidytools/ai-web-data-extractor

AI web scraper and AI extractor: URL to JSON. Name the fields or write a prompt, and an LLM reads each page and returns structured data. One row per list item, follows detail links, reads PDF and image documents. $0.01 per page with data. Failed pages are free.

Yukai Lin

Firmographics — Company Website Enrichment

tidytools/company-website-enrichment

Firmographics from each company's own website: industry, business model, stated size clues and contact details. Enter company names, domains or Google Maps leads; rows map back to the source. $6/1,000.

Yukai Lin

PDF & DOCX to Markdown — Document Extractor for LLM/RAG

fetchbase/document-to-markdown

Convert PDF and Word (DOCX) documents into clean Markdown, text, or JSON. Smart PDF paragraph reflow, page markers for RAG citations, full DOCX structure (headings, lists, tables), custom auth headers. No browser — parses in seconds. Charged per page processed — no startup fee.

Fetchbase

OCR API - Image to Text, Photo to Text & Receipt OCR

tidytools/image-to-text-ocr

Bulk image OCR and photo to text for receipts, screenshots and document photos. Extract text from image URLs, datasets or base64 as plain text or Markdown; optional receipt fields and table rows. $0.003 per image with text on Free and Bronze; no-text and failed results are free.

Yukai Lin

PDF to Markdown Converter - AI-Powered with OCR & Tables

clearpath/pdf-to-markdown-api

Convert PDFs to clean Markdown with GPU-accelerated AI. Extracts tables, LaTeX formulas, and images from complex layouts. Supports OCR for scanned docs in 8 languages. Batch process hundreds of PDFs in parallel via URL, upload, or API.

ClearPath

SEO Audit Tool - SEO Checker, Site Audit & Core Web Vitals

tidytools/seo-audit-crawler

SEO audit tool and site audit crawler for technical SEO, JavaScript sites too: 0-100 score and a fix hint per issue, site report (duplicate titles, broken pages, missing H1, meta, alt, sitemap, hreflang), optional Core Web Vitals. $5 per 1,000 pages; failed pages are free.

Yukai Lin

Website to Markdown Crawler - Content Crawler for LLM & RAG

tidytools/website-markdown-crawler

Website to Markdown crawler for RAG and LLMs: crawl a website or docs site into clean Markdown (URL to Markdown, HTML to Markdown) with RAG chunks. Sitemaps, JavaScript pages, linked PDFs and Word. $1/1k pages.

Yukai Lin

PDF Text Extractor — Text, Markdown, Tables and OCR

lergassy/pdf-text-extractor

PDF text extractor by URL, upload or base64: full text, per-page text, Markdown, tables and metadata. Scanned pages are read with OCR. $0.003 per PDF.