Documents tools
Document APIs extract text or tables, inspect and rearrange PDFs, and render documents to PDF. Agents and scripts can use them when document parsing, OCR or layout requires a dedicated engine and guarded fetching. csv-to-json accepts delimited text and auto-detects the delimiter; xlsx-to-json reads a spreadsheet workbook and converts dates to ISO strings. Both return header-keyed rows or arrays. json-to-csv takes JSON objects, infers or accepts columns, and JSON-encodes nested values.
docx-to-markdown converts a word-processing document with warnings for content that did not translate. pptx-to-text extracts slide body text in order; epub-to-text returns chapter text in reading order and Dublin Core metadata. pdf-to-text reads the text layer page by page; pdf-to-markdown infers headings from font size. Neither performs OCR or guarantees complete extraction. Unavailable character mappings can leave empty or partial text without an error. ocr-image-to-text reads images with Tesseract and returns text with mean confidence.
pdf-metadata returns page count, document-info fields, version and encryption status without rendering. pdf-split takes a page selection; pdf-merge concatenates source PDFs in order. Both return a PDF encoded as base64. html-to-pdf renders a web page or inline HTML; markdown-to-pdf renders Markdown. Both return a PDF encoded as base64 with its page count. PDF Markdown conversion is best-effort, without exact layout preservation. CSV output does not neutralize spreadsheet formulas: quoting handles delimiters, quotes and newlines while preserving formula prefixes.
01APIs
| API | What it does | Price | Max input | Max duration | Timeout |
|---|---|---|---|---|---|
| CSV to JSON API | Parses a CSV/TSV document into JSON rows, keyed by a header row or as arrays; the delimiter is auto-detected. | $0.005 per call | 25 MB | none | 30 s |
| DOCX to Markdown API | Converts a Word .docx to Markdown, surfacing anything that did not translate as warnings. | $0.005 per call | 25 MB | none | 40 s |
| EPUB to Text API | Extracts an EPUB’s reading-order text and Dublin Core metadata, chapter by chapter. | $0.005 per call | 25 MB | none | 45 s |
| HTML to PDF API | Renders a web page or an inline HTML string to a PDF, returned base64-encoded with its page count. | $0.005 per call | 5 MB | none | 12 s |
| JSON to CSV API | Renders JSON objects as raw CSV with no spreadsheet formula protection; columns are inferred or given, nested values are JSON-encoded. | $0.005 per call | 25 MB | none | 30 s |
| Markdown to PDF API | Renders a Markdown document to a PDF, returned base64-encoded with its page count. | $0.005 per call | 2 MB | none | 12 s |
| OCR Image to Text API | Reads the text out of an image (scan, screenshot, photo) with Tesseract, returned with a mean confidence. | $0.005 per call | 10 MB | none | 45 s |
| PDF Merge API | Concatenates 2–8 source PDFs, in order, into one PDF returned base64-encoded. Maximum output PDF size: 25 MiB before base64 encoding. | $0.005 per call | 8 MB | none | 45 s |
| PDF Metadata API | Reads a PDF's page count, document-info fields, version and encryption flag without rendering it. | $0.005 per call | 25 MB | none | 25 s |
| PDF Split API | Extracts a 1-indexed page selection (e.g. "1,3-4") from a PDF into one new PDF, returned base64-encoded. Maximum output PDF size: 25 MiB before base64 encoding. | $0.005 per call | 25 MB | none | 30 s |
| PDF to Markdown API | Converts a PDF to Markdown, inferring headings from font size (best-effort, not layout-perfect; no OCR). | $0.005 per call | 25 MB | none | 40 s |
| PDF to Text API | Extracts the text layer of a PDF, page by page, in reading order (no OCR). | $0.005 per call | 25 MB | none | 40 s |
| PPTX to Text API | Extracts the slide text of a PowerPoint .pptx, slide by slide, in order (body text only, up to 1,000 slides). | $0.005 per call | 25 MB | none | 40 s |
| XLSX to JSON API | Reads an Excel .xlsx into JSON rows, keyed by a header row or as arrays; dates become ISO strings. Archives are limited to 64 worksheets. | $0.005 per call | 25 MB | none | 40 s |
02Conversions
- CSV to JSON
- DOCX to Markdown
- EPUB to plain text
- GIF to plain text
- HTML to PDF
- JPEG to plain text
- JSON to CSV
- Markdown to PDF
- PDF to Markdown
- PDF to plain text
- PNG to plain text
- PPTX to plain text
- TIFF to plain text
- TSV to JSON
- WebP to plain text
- XLSX to JSON
03Questions
- Do the PDF text extractors perform OCR or guarantee complete text?
- No. pdf-to-text and pdf-to-markdown extract the text layer without OCR. They do not fetch external CMap or standard-font data. A PDF that needs unavailable predefined CMaps can yield empty or partial text without an error. A successful response does not certify completeness, and truncated reports only the max_pages limit.
- Does json-to-csv protect against spreadsheet formulas?
- No. It preserves formula prefixes in headers and string values without adding apostrophes or trimming tabs and carriage returns. CSV quoting escapes delimiters, quotes and newlines but does not neutralize formulas. Records are separated by CRLF.
- How do PDF splitting and merging differ?
- pdf-split extracts a page selection from a source PDF into a new PDF. pdf-merge concatenates source PDFs in order. Both return the resulting PDF encoded as base64.