bhāṣā śālā
language house
An etymologically-informed reader for Indian language texts. Word-level transliteration, translation, and etymological connections across hundreds of Indic languages.
Transliteration, translation, and grammar for every word. Hover any word to see its full breakdown with sources from multiple dictionaries.
Trace word origins across Indo-Aryan, Dravidian, and Munda language families. Built on Jambu, CDIAL, DEDR, and Wiktionary data.
Support for Gujarati, Devanagari, and more Indic scripts with both rule-based and AI-assisted transliteration.
PDFs are processed with Gemini 2.5 Flash to extract text and word bounding boxes
Each word is looked up across Wiktionary (16 languages), Jambu/CDIAL (290K forms), and Monier-Williams (160K entries)
An LLM (Llama 3.3 70B via Groq) selects the best sense for each word in context
Cross-linguistic cognate data spanning hundreds of Indic languages is assembled into interactive etymology visualizations