Libraries for developers

Converts old Tibetan fonts to Unicode. Includes a command-line tool that converts Word and RTF files while keeping their formatting.

• Free
• Open source

Converts mantras from Unicode Tibetan into IAST and phonetics. Available on npm.

• Free
• Open source

A simple tool to normalize Tibetan Unicode strings.

• Free
• Open source

Useful regular expressions for dealing with Unicode Tibetan, such as splitting a text into Tibetan groups or recognizing punctuation.

• Free
• Open source

A Python library that transliterates Tibetan-encoded Sanskrit mantras into IAST and phonetics. Shares its data with the JavaScript version.

• Free
• Open source

The shared replacement-map data (Tibetan, IAST, phonetics) used by the JavaScript and Python transliteration libraries. Published for both npm and Python.

• Free
• Open source

Deconstructs a single Unicode Tibetan syllable into its parts - prefix, superscribed, root, subscribed, vowel, suffix and more.

• Free
• Open source

Converts Tibetan Unicode text into phonetics based on customizable sets of rules. The engine behind the Tibetan to Phonetics web app.

• Free
• Open source

A JavaScript library to convert ANSI-encoded Tibetan text to Unicode, usable as an ES module, in CommonJS or directly in the browser.

• Free
• Open source

A JavaScript port of Botok, OpenPecha's Tibetan word tokenizer, with Sanskrit detection. Runs in Node.js with no dependencies. The linguistic work and the dictionary are by the Botok team at OpenPecha.

• Free
• Open source

Scripts that run Tibetan OCR on images and PDFs through Google Drive and write the result as text and Word files. Includes a quick-snip shortcut for macOS. Needs your own Google API credentials.

• Mac
• Windows
• Free

BDRC's page on Hugging Face, "making Buddhist texts available to everyone using AI (OCR, search, etc.), focusing primarily on Tibetan". Hosts open OCR models and datasets.

• Web
• Free
• Open source

A Python library for tokenizing Tibetan text into words, which can also add lemmas, part-of-speech tags and clean forms.

• Free
• Open source

Fixes incorrect or incomplete PDF ToUnicode maps so that text extraction, search and copy-paste return correct Unicode. Primarily for Tibetan stacked syllables in Monlam, Himalaya and Jomolhari fonts, and for some legacy fonts.

• Free
• Open source

Typesets Tibetan text in the traditional pecha layout with LaTeX. Builds on the cTib4TeX package by Oliver Corff and adds multilingual headers and Tibetan page numbering.

• Free
• Open source

A Python script that converts PDFs using non-Unicode Tibetan fonts into Unicode text. A work in progress, with a long list of supported legacy fonts.

• Free
• Open source

Python utilities for converting between Extended Wylie (EWTS) and Tibetan Unicode.

• Free
• Open source

Converts files between Tibetan encoding schemes and file formats (text, RTF, HTML), including twelve legacy fonts, Unicode and Wylie variants. A command-line program compiled from C; its README notes some known bugs.

• Free
• Open source