arxiv
PublishedJune 29, 2026 at 4:00 AM
—neutral
ZONOS2 Technical Report
Publisher summary· verbatim
arXiv:2606.24320v2 Announce Type: replace-cross Abstract: We present ZONOS2 8B, our latest TTS model, which achieves state-of-the-art naturalness, prosody, and voice cloning fidelity. We improve upon Zonos-v0.1 across scale, data, and training recipe. We scale the model from 1.6B to 8B total paramet
Stay posted· Newsletter
A 5-min weekly brief — top movers, price watch, story of the week.
Discussion
No replies yet. Be first.
Related coverage
More from ARXIV
arxivIMEX Interaction-Based Model Explanation24marxivDialogueVPR: Towards Conversational Visual Place Recognition24marxivHuman AI Construction of Bayesian Networks for Operational Decision Support -- A Virtual Survey Approach24marxivCapability from Access Structure, Not Scale: Lower Bounds and Pre-Registered Tests for Hybrid Sequence Models24mThe Bubble Brief
WEEKLYRead AI insights every Tuesday — top movers, new releases, story of the week.
Originally published on arxiv ↗