Open-Source TTS Model OmniVoice Covers 600+ Languages at 40x Real-Time

k2-fsa released OmniVoice, a fully open-source zero-shot TTS model supporting 600+ languages with 40x real-time inference speed and voice cloning via text prompts, already at 15.1k GitHub stars.

2026-10-20 ~ 2026-10-20 · 2 related posts

• OmniVoice: open-source TTS with 600+ languages and 40x realtime cloning — abhishek__AI · 2026-10-20

1 near-duplicate retellings: abhishek__AI