Credits & Sources

Phonaria uses open source projects, linguistic research, and freely licensed resources.

CMU Pronouncing Dictionary

Transcription uses the CMU Pronouncing Dictionary from Carnegie Mellon University. The dictionary contains over 134,000 North American English words with phonetic transcriptions and is released under a BSD license.

View CMUdict on GitHub BSD

wordfreq Word Frequency Data

Curated word lists for client-side lookup are generated using wordfreq by Robyn Speer. The library combines frequency data from Google Books Ngrams, OpenSubtitles, SUBTLEX, Wikipedia, and other corpora.

View wordfreq on GitHub CC BY-SA 4.0

Phonetic Data

Articulatory descriptions, phoneme features, and IPA classifications draw from standard phonetic references and linguistics research.