Skip to content

docs: add supported formats section with usage and limitations #1631

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
zhaorong566 wants to merge 1 commit into
base: main
Choose a base branch
from
+41 −0
Open

docs: add supported formats section with usage and limitations #1631

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
41 changes: 41 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -30,6 +30,47 @@ MarkItDown currently supports the conversion from:
- EPubs
- ... and more!

## Supported Formats

### Excel (.xlsx, .xls)
- Each sheet is converted to a separate Markdown table
- Supports currency formatting (e.g., `$1,199.00`, `€299.50`)
- Install dependencies: `pip install 'markitdown[xlsx]'` for `.xlsx`, `pip install 'markitdown[xls]'` for `.xls`
- **Known limitations:** Complex merged cells and conditional formatting are not preserved

### PDF (.pdf)
- Text content is extracted and converted to Markdown
- Install dependencies: `pip install 'markitdown[pdf]'`
- **Known limitations:** Complex multi-column layouts may not preserve reading order; scanned PDFs require OCR plugin

### PowerPoint (.pptx)
- Slide titles, text content, and tables are extracted
- Install dependencies: `pip install 'markitdown[pptx]'`
- **Known limitations:** Slide images are not extracted by default (use `markitdown-ocr` plugin for image text)

### Word (.docx)
- Headings, paragraphs, tables, and lists are preserved
- Install dependencies: `pip install 'markitdown[docx]'`

### Images (.jpg, .png, etc.)
- Extracts EXIF metadata
- Optionally generates image descriptions using an LLM (requires `llm_client` and `llm_model`)

### Audio (.wav, .mp3)
- Extracts EXIF metadata
- Optionally transcribes speech to text
- Install dependencies: `pip install 'markitdown[audio-transcription]'`

### HTML
- Converts HTML structure to Markdown, preserving headings, links, and tables
- No additional dependencies required

### Others
- **CSV / JSON / XML**: Converted to readable Markdown text
- **YouTube URLs**: Fetches video transcript if available (`pip install 'markitdown[youtube-transcription]'`)
- **EPub**: Extracts chapter text content
- **ZIP**: Iterates over all files inside and converts each one

## Why Markdown?

Markdown is extremely close to plain text, with minimal markup or formatting, but still
Expand Down