AIMarkTechPostabout 1 hour ago
Gradium Open-Sources Phonon TTS Model
1 min read
Gradium open-sources Phonon, a 31M-parameter on-device text-to-speech model under Apache 2.0. The English version fits in 64.5 MB and runs on CPUs, phones, Raspberry Pi 5, browsers, and NVIDIA GPUs without requiring a GPU or cloud calls.
Level
Hype check
Tap to vote and see what everyone thinks.
