cs.SDNov 12, 2026

ZONOS3-Mini Technical Report

Authors: Gabriel Clark, Sofian Mejjoute, George Close, Beren Millidge

Organizations: Zyphra · San Francisco, CA

Abstract

ZONOS3-Mini is an ultra-compact, ultra-fast, zero-shot voice-cloning TTS model. The model can run in real time on a laptop or smartphone. For its latency and size, it achieves state-of-the-art accuracy and cloning fidelity. To achieve this we propose a latent MoE backbone with only 886M parameters (100M active per token) and a new audio codec, Zyphra Audio Codec 1 (ZAC-1), which represents 44.1 kHz audio at a 15 Hz frame rate. On the new ZTTS2-Eval benchmark, ZONOS3-Mini reaches a 6.71% macro-average WER over 55 language sets (35 clean and 20 in the wild), which is competitive with larger and slower state-of-the-art models. We release the model weights, inference, and training code.

Figures & tables

Explore similar work

CardsList
  1. ZONOS2 Technical Report

    Jun 23, 2026Gabriel Clark, Sofian Mejjoute, Mohamed Osman +2TTS SynthesisStreaming TTS Synthesis

  2. M5-TTS: A Mini-Scale Multilingual and Multi-Dialect Text-to-Speech Language Model with Multi-Token Prediction

    Nov 6, 2026Wenhao Li, Jingbin Hu, Shengming Ling +20TTS SynthesisMultilingual TTS Synthesis