MongoDB - Build AI That Scales
Mini toolsZONOS2
By Zyphra AI
ZONOS2 is Zyphra’s real-time TTS model built for expressive, naturalistic speech and high-fidelity zero-shot voice cloning. Zyphra describes it as an MoE-based speech model trained on more than 6 million hours of varied multilingual speech, designed to deliver low-latency generation while preserving speaker similarity, prosody, and naturalness across a wide range of voices and languages. It is aimed at voice agents, cloning workflows, multilingual speech synthesis, and expressive production-quality TTS.
New
Multimodal
Gen 3
Overview
ZONOS2 is Zyphra’s open-source real-time text-to-speech model with MoE architecture, high-fidelity zero-shot voice cloning, and multilingual expressive speech generation.
About Zyphra AI
Superintelligence that Empowers.
Zyphra is a full stack open source superintelligence company based in San Francisco, California.
Our mission is to build human-aligned AI that helps individuals and organizations reach their fullest potential.
Tools using ZONOS2
No tools found for this model yet.
Last updated: June 15, 2026
