# Feature catalog — microsoft/markitdown

> Canonical page: https://codevetter.com/unpack/markitdown/feature-catalog

# Feature catalog — microsoft/markitdown

Scanned commit b8f79c57ebc0044be41323d89b2a45d3fda8460e (2026-09-21). Generated by codevetter codevetter 1.12.0 on 2026-09-22.

User-facing surface is three-fold: the `markitdown` CLI, the MarkItDown Python API (convert/convert_local/convert_stream/convert_uri/convert_response), and the `markitdown-mcp` server tool. Format coverage spans office docs (docx/xlsx/xls/pptx), PDF, images, audio, HTML plus URL-specialized converters (Wikipedia, YouTube, Bing SERP), EPUB, Outlook .msg, Jupyter notebooks, CSV, ZIP archives, and plain text. Cloud integrations offer Azure Document Intelligence and Azure Content Understanding as opt-in converters, and LLM-based image captions via a caller-supplied OpenAI-compatible client.
- The CLI accepts a filename or stdin (sys.stdin.buffer wrapped in BytesIO), writes markdown to stdout or -o file, and supports hint flags -x/-m/-c that populate a StreamInfo passed to convert(). — [packages/markitdown/src/markitdown/__main__.py#L251-263](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L251-L263) [packages/markitdown/src/markitdown/__main__.py#L180-188](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L180-L188)
- --use-docintel / -d requires -e/--endpoint or env var MARKITDOWN_DOCINTEL_ENDPOINT and registers DocumentIntelligenceConverter, which calls Azure's prebuilt-layout model via DocumentIntelligenceClient.begin_analyze_document with markdown output format. — [packages/markitdown/src/markitdown/__main__.py#L207-218](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L207-L218) [packages/markitdown/src/markitdown/converters/_doc_intel_converter.py#L241-258](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_doc_intel_converter.py#L241-L258)
- --use-cu requires --cu-endpoint or env MARKITDOWN_CU_ENDPOINT, accepts --cu-analyzer and --cu-file-types, and registers ContentUnderstandingConverter which supports documents, email, images, video and audio per the ContentUnderstandingFileType enum. — [packages/markitdown/src/markitdown/__main__.py#L219-247](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L219-L247) [packages/markitdown/src/markitdown/converters/_cu_converter.py#L55-98](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_cu_converter.py#L55-L98)
- --use-plugins / --list-plugins controls third-party plugin loading; plugins are disabled by default and discovered via the 'markitdown.plugin' entry-point group. — [packages/markitdown/src/markitdown/__main__.py#L126-137](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L126-L137) [packages/markitdown/src/markitdown/__main__.py#L190-205](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L190-L205)
- --keep-data-uris controls whether base64 data URIs are kept in output; default behavior truncates them via the keep_data_uris option of _CustomMarkdownify. — [packages/markitdown/src/markitdown/__main__.py#L139-143](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/__main__.py#L139-L143) [packages/markitdown/src/markitdown/converters/_markdownify.py#L35-39](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_markdownify.py#L35-L39)
- DocxConverter subclasses HtmlConverter: it pre-processes the .docx zip (OMML math -> LaTeX via converter_utils/docx), merges caller style_map + embedded style map + a default 'u => u' underline rule, runs mammoth.convert_to_html, optionally adapts embedded images through an overridable _image_to_html hook, then converts the HTML via _CustomMarkdownify. — [packages/markitdown/src/markitdown/converters/_docx_converter.py#L43-143](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_docx_converter.py#L43-L143) [packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py#L34-80](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converter_utils/docx/pre_process.py#L34-L80)
- PdfConverter (589 lines) uses pdfminer.six and pdfplumber with helpers to emit aligned Markdown tables (_to_markdown_table), merge MasterFormat partial numbering, and extract form content; missing deps raise MissingDependencyException pointing at the [pdf] extra. — [packages/markitdown/src/markitdown/converters/_pdf_converter.py#L60-120](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_pdf_converter.py#L60-L120)
- XlsxConverter/XlsConverter share one module using pandas.read_excel with openpyxl/xlrd engines, including a repair path that renames the non-schema 'showZeroes' attribute inside <sheetView> start tags only. — [packages/markitdown/src/markitdown/converters/_xlsx_converter.py#L14-60](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_xlsx_converter.py#L14-L60)
- ImageConverter emits exiftool-extracted metadata fields (ImageSize, GPSPosition, etc.) and, when llm_client+llm_model kwargs are present, calls _get_llm_description which base64-embeds the image into an OpenAI chat.completions vision request. — [packages/markitdown/src/markitdown/converters/_image_converter.py#L39-138](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_image_converter.py#L39-L138)
- AudioConverter combines exiftool metadata with SpeechRecognition transcription (recognize_google) for wav/mp3/m4a/mp4 after pydub conversion to wav; missing pydub/SpeechRecognition raises MissingDependencyException for the [audio-transcription] extra. — [packages/markitdown/src/markitdown/converters/_audio_converter.py#L46-101](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_audio_converter.py#L46-L101) [packages/markitdown/src/markitdown/converters/_transcribe_audio.py#L29-58](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_transcribe_audio.py#L29-L58)
- YouTubeConverter accepts HTML streams whose stream_info.url parses to a youtu.be/youtube.com video id, scrapes metadata from the HTML, and optionally fetches transcripts via youtube-transcript-api; WikipediaConverter and BingSerpConverter similarly gate accepts() on the source URL. — [packages/markitdown/src/markitdown/converters/_youtube_converter.py#L41-80](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_youtube_converter.py#L41-L80) [packages/markitdown/src/markitdown/converters/_wikipedia_converter.py#L21-46](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_wikipedia_converter.py#L21-L46) [packages/markitdown/src/markitdown/converters/_bing_serp_converter.py](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_bing_serp_converter.py)
- EpubConverter opens the EPUB zip in-memory, parses META-INF/container.xml and content.opf with defusedxml.minidom, extracts Dublin Core metadata, resolves spine hrefs (with percent-decoding fallback), and converts each spine HTML file through HtmlConverter. — [packages/markitdown/src/markitdown/converters/_epub_converter.py#L55-134](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_epub_converter.py#L55-L134)
- OutlookMsgConverter parses .msg OLE files with olefile, including manual decoding of the __properties_version1.0 stream and a CODEPAGE_CODECS table mapping ~30 Windows code page IDs to Python codecs for ANSI-encoded bodies. — [packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py#L21-75](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_outlook_msg_converter.py#L21-L75)
- ZipConverter recursively converts each archive member by calling self._markitdown.convert_stream on the decompressed bytes, prefixing each result with '## File: <name>' and silently skipping members that raise UnsupportedFormatException or FileConversionException. — [packages/markitdown/src/markitdown/converters/_zip_converter.py#L87-130](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown/src/markitdown/converters/_zip_converter.py#L87-L130)
- The markitdown-mcp package exposes a single MCP tool convert_to_markdown(uri) that accepts http:, https:, file: and data: URIs and returns markdown text, mapping internal exceptions to sanitized ToolError messages. — [packages/markitdown-mcp/src/markitdown_mcp/__main__.py#L19-47](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown-mcp/src/markitdown_mcp/__main__.py#L19-L47)
- markitdown-ocr ships four enhanced converters (PdfConverterWithOCR, DocxConverterWithOCR, PptxConverterWithOCR, XlsxConverterWithOCR) that extract embedded images and OCR them via an LLMVisionOCRService wrapping an OpenAI-compatible chat.completions call. — [packages/markitdown-ocr/src/markitdown_ocr/_plugin.py#L49-68](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown-ocr/src/markitdown_ocr/_plugin.py#L49-L68) [packages/markitdown-ocr/src/markitdown_ocr/_ocr_service.py#L24-111](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown-ocr/src/markitdown_ocr/_ocr_service.py#L24-L111) [packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py#L1-50](https://github.com/microsoft/markitdown/blob/b8f79c57ebc0044be41323d89b2a45d3fda8460e/packages/markitdown-ocr/src/markitdown_ocr/_pdf_converter_with_ocr.py#L1-L50)

Every claim links to its cited files at the pinned commit. Citations identify source evidence; they do not establish runtime correctness. Independent CodeVetter scan — not reviewed by upstream maintainers.

## Public product links

- [CodeVetter](https://codevetter.com/)
- [Download](https://codevetter.com/download)
- [Documentation](https://codevetter.com/docs/)
- [Source](https://github.com/Codevetter/codevetter)