arxiv4d ago
OmniVoice: Towards Omnilingual Zero-Shot Text-to-Speech with Diffusion Language Models
arXiv:2604.00688v3 Announce Type: replace Abstract: We present OmniVoice, a massively 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 discret