A speech model small enough to live on the device
Gradium's Phonon runs without a server, in about 65 MB and 75 MB sizes, across five languages. The English 31-million-parameter model is Apache 2.0. The other models are non-commercial. Local does not mean "sell it in your app."
- Verdict
- Watch Promising, but something is missing: access, pricing, or proof.
- For
- people who want on-device speech
- Why it matters
- The English 31-million-parameter model is Apache 2.0. The other models are non-commercial.
- Next check
- Recheck the model card before you ship a language other than that English model.
- Published
- Filed
- By
- The Loaded Tokens desk
- Topic
- Voice & audio
- Sources
- Hugging Face
Sources & limits: This is our recap, not a copy of the original. The links above are the pages we read. We didn't test it ourselves.
Corrections: if a fact is wrong, email hello@loadedtokens.com.