ZONOS3-Mini 技术报告：886M 参数零样本语音克隆 TTS 模型开源
ZONOS3-Mini Technical Report
AI 导读
ZONOS3-Mini 是一款超紧凑、超快的零样本语音克隆 TTS 模型，可在笔记本或手机上实时运行。
正文 · 原文
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.
| Comments: | 19 pages, 4 figures, 12 tables. Model weights: this https URL ; code: this https URL |
| Subjects: | Sound (cs.SD); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2611.16525 [cs.SD] |
| (or arXiv:2611.16525v1 [cs.SD] for this version) | |
| https://doi.org/10.48550/arXiv.2611.16525 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Gabriel Clark [view email]
[v1]
Thu, 12 Nov 2026 09:24:22 UTC (328 KB)
来源：arXiv cs.AI · arxiv.org