OmniVoice open-sources diffusion-based TTS with zero-shot voice cloning in 600+ languages

tom_doerr · x · 2026-09-04

k2-fsa has open-sourced OmniVoice, a massively multilingual zero-shot TTS model supporting over 600 languages — claimed to be the broadest coverage among zero-shot TTS models. It already has 9.7k GitHub stars.

Original post →

More from Multimodal

Multimodal channel →