Phonon
Phonon is Gradium’s private-beta 100M-parameter on-device text-to-speech model for low-latency, offline, privacy-sensitive voice generation.
- Type
- Video
- Weights
- Open
More from Gradium
3
About Gradium
1
Gradium develops audio language models (ALMs) providing ultra-low latency text-to-speech, speech-to-text, and voice cloning capabilities via API. Spun out of French AI lab Kyutai, it builds voice AI infrastructure for developers and enterprise voice agents, targeting sub-200ms latency with human-like expressiveness and multilingual support.