AI RESEARCH
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
arXiv CS.CL
•
ArXi:2604.00688v2 Announce Type: new We present OmniVoice, a massive multilingual zero-shot text-to-speech (TTS) model that scales to over 600 languages. At its core is a novel diffusion language model-style discrete non-autoregressive (NAR) architecture. Unlike conventional discrete NAR models that suffer from performance bottlenecks in complex two-stage (text-to-semantic-to-acoustic) pipelines, OmniVoice directly maps text to multi-codebook acoustic tokens. This simplified approach is facilitated by two key technical innovations: (1) a full-codebook random masking strategy for efficient.