Gradium open-sources Phonon, a 31M-parameter on-device TTS model

A tiny Apache-2.0 TTS model makes on-device speech synthesis practical.

Phonon is a small text-to-speech model that converts written text into spoken audio, designed to run on-device. Gradium released its 31M-parameter weights under Apache 2.0.

Name

Phonon

Params

31M

License

Apache 2.0

Domain

creative

Read it at MarkTechPost →

Coverage: 3 sources, in order

1. 22 Oct 16:56 MarkTechPost Read the article →
2. 22 Oct 16:56 MarkTechPost Read the article →
3. 22 Oct 16:56 MarkTechPost Read the article →

← Front page