AI Merchant Name Translation
Foreign merchant names from Cyrillic, Greek, or Arabic bank statements get normalized to readable Latin — on your device, without sending anything to a server.
Why foreign merchant names break expense search
Bank statements from Ukrainian, Greek, or Arabic-script banks come back full of unreadable merchant names — useless for search or analytics. Budgie's on-device normalizer runs each merchant string through the LLM, gets a clean Latin name plus search keywords, and stores both.
Original Cyrillic or Greek strings are preserved for receipt-matching and audit; the normalized form is what your search queries hit. No data ever leaves your device.
What you get
Cyrillic, Greek, Arabic, CJK, and more — any non-Latin script the on-device LLM understands
Original merchant string preserved for receipt-matching and audit
Translated form indexed by embeddings — semantic search hits whatever you remember
On-device — no merchant string ever leaves your phone
Manual override per merchant if the LLM gets it wrong
How it works
Each new transaction's title flows through a translation queue. The LLM proposes (translatedName, keywords); both are saved alongside the original. Embeddings then index the translated form for semantic search.
Frequently Asked Questions
Which scripts are supported?
Are the original merchant strings kept?
What if the LLM mistranslates?
Does this run on every transaction?
Related Features
Read More on the Blog
Ready to take Budgie for a spin?
Join the waitlist — be first to try the offline-first expense tracker.