theaicatalog
Hugging Face ยท Models

Phonon TTS model runs speech on devices without a network

Hugging Face released Phonon, a small text-to-speech model that runs on a user's own device, so no server or network is needed and typed text stays on the device. The Phonon 31m model speaks English and uses the Apache 2.0 license, so it can be used for free, including in commercial products. The Phonon 40m model covers English, French, German, Spanish and Portuguese under a non-commercial license. Hugging Face says Phonon was downloaded more than 200,000 times in its first two weeks.