Audio Language Model5 min read
Gradium Open-Sources Phonon, a 31M-Parameter On-Device TTS Model Under Apache 2.0
Gradium has open-sourced Phonon, a family of on-device text-to-speech models. The English Phonon 31m ships under Apache 2.0, fits in 64.5 MB, and starts speaking in about 7 ms on a laptop CPU.
By Asif RazzaqMarkTechPost

Read the full story
Originally published by MarkTechPost on Oct 22, 2026.
Comments
Sign in to join the discussion.