> ## Documentation Index
> Fetch the complete documentation index at: https://docs.aryn.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Supported Formats and Languages

> Here are the input and output formats, and OCR languages supported by Aryn DocParse

## Input Formats

Aryn DocParse supports the following input formats:

* `.pdf`
* `.docx`
* `.doc`
* `.pptx`
* `.ppt`
* `.csv`
* `.jpg` (`.jpeg`)
* `.png`
* `.bmp`
* `.tiff`
* `.html`
* `.odt`
* `.rtf`
* `.txt`
* `.xls`
* `.xlsx`
* `.xml`
* `.svg`
* `.webp`
* `.wmf`
* `.emf`
* `.mml`
* `.ods`
* `.xhtml`
* `.odp`
* `.odg`
* `.odf`
* `.ots`
* `.xltx`
* `.fods`
* `.xlt`
* `.slk`

## Output Formats

Aryn DocParse supports the following output formats:

* `.json`
* `.md`
* `.html`

## OCR Languages

Aryn DocParse supports the following OCR languages. The default is `english`:

* Abaza: `abaza`
* Adyghe: `adyghe`
* Afrikaans: `afrikaans`
* Albanian: `albanian`
* Angika: `angika`
* Arabic: `arabic`
* Avar: `avar`
* Azerbaijani: `azerbaijani`
* Belarusian: `belarusian`
* Bhojpuri: `bhojpuri`
* Bihari: `bihari`
* Bosnian: `bosnian`
* Bulgarian: `bulgarian`
* Chinese: `chinese`
* Chinese (Traditional): `chinese_traditional`
* Croatian: `croatian`
* Czech: `czech`
* Danish: `danish`
* Dargwa: `dargwa`
* Dutch: `dutch`
* English: `english`
* Estonian: `estonian`
* French: `french`
* German: `german`
* Hindi: `hindi`
* Hungarian: `hungarian`
* Icelandic: `icelandic`
* Indonesian: `indonesian`
* Ingush: `ingush`
* Irish: `irish`
* Italian: `italian`
* Japanese: `japanese`
* Kabardian: `kabardian`
* Konkani: `konkani`
* Korean: `korean`
* Kurdish: `kurdish`
* Lak: `lak`
* Latvian: `latvian`
* Lezghian: `lezghian`
* Lithuanian: `lithuanian`
* Magahi: `magahi`
* Maithili: `maithili`
* Malay: `malay`
* Maltese: `maltese`
* Maori: `maori`
* Marathi: `marathi`
* Mongolian: `mongolian`
* Nagpuri: `nagpuri`
* Nepali: `nepali`
* Newari: `newari`
* Norwegian: `norwegian`
* Occitan: `occitan`
* Persian: `persian`
* Polish: `polish`
* Portuguese: `portuguese`
* Romanian: `romanian`
* Russian: `russian`
* Serbian (Cyrillic): `serbian_cyrillic`
* Serbian (Latin): `serbian_latin`
* Slovak: `slovak`
* Slovenian: `slovenian`
* Spanish: `spanish`
* Swahili: `swahili`
* Swedish: `swedish`
* Tabassaran: `tabassaran`
* Tagalog: `tagalog`
* Tamil: `tamil`
* Telugu: `telugu`
* Turkish: `turkish`
* Ukrainian: `ukrainian`
* Urdu: `urdu`
* Uyghur: `uyghur`
* Uzbek: `uzbek`
* Vietnamese: `vietnamese`
* Welsh: `welsh`

For information, refer to the [output structure](./output_structure) page. For a walkthrough with a document, see the [output walkthrough](./tutorials/output_walkthrough) page.