AI & ML
ZONOS3-Mini Technical Report
arXiv cs.SD0 views
arXiv:2611.16525v2 Announce Type: replace 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.
Source:https://arxiv.org/abs/2611.16525PreviousMarimba: A System One Model for SpeechNextThe Alignment Curse: Modality Alignment Supercharges Audio Attacks via Text Transfer
Related posts
Building an AI Agent Backend with FastAPI: From User Request to AI Response
0dev.to AI

SoduWork Custom Model Setup: Connect an OpenAI-Compatible Gateway and Handle the 180-Second Stall
0dev.to AI
AI startup hiring snapshot, 16 November 2026: 6,481 open roles, half at four companies
0dev.to AI
EC2 已经停止,账单为什么还在变?用资源清单代替猜测
0dev.to AWS

Amazon Black Friday 2026:5 Key Metrics and a Step-by-Step Data Collection Guide
0dev.to AWS
How to Trim Audio for an Online Course Lesson — Free, in Your Browser
0dev.to WebDev