Show HN: Omni Voice – AI Voice Cloning and Text-to-Speech Platform

Category: ai-ml

Tags: ai-voice, text-to-speech, voice-cloning, multilingual, diffusion-models

Score: 8.0/10 (Innovation: 8, Technical: 9, Documentation: 8, Utility: 7)

OmniVoice is a state-of-the-art, massive multilingual text-to-speech (TTS) model supporting over 600 languages with zero-shot voice cloning and voice design capabilities. It's interesting because it uses a novel diffusion language model-style architecture to achieve high-quality speech generation with exceptionally fast inference speeds (40x real-time).

Target audience: ai researchers, ml engineers, product developers, content creators

Repository: https://omnivoice.app · Python · Apache-2.0

View on Hacker News