ZONOS2 8B TTS model achieves state-of-the-art naturalness and voice cloning

Arxiv CS.SD (Sound/Audio ML)

ZONOS2 8B is a text-to-speech model scaled from 1.6B to 8B parameters, achieving state-of-the-art results in naturalness, prosody, and voice cloning fidelity. The model improves upon Zonos-v0.1 via better data and training.

zonostext-to-speech

Arxiv CS.SD (Sound/Audio ML)·Gabriel ClarkSofian MejjouteMohamed OsmanGeorge CloseBeren Millidge

23 hours ago