Back to models
OV
Local model

k2-fsa/OmniVoice

OmniVoice

Massive language coverage

Languages

646

License

Apache 2.0

Modes

Clone + design

OpenVox fit

Global narration

Model overview

Built into OpenVox for private local voice generation.

Hugging Face

OmniVoice is a massively multilingual zero-shot TTS model built for broad language coverage, voice cloning, voice design, and fast local speech generation.

OmniVoice supports 646 languages across zero-shot, multilingual, voice-cloning, and voice-design workflows.

Voice attributes include gender, age, pitch, dialect/accent, and whisper-style control.

OpenVox uses OmniVoice where language reach matters more than anything else, especially long-tail and regional coverage.

OpenVox does not provide celebrity voice models and does not permit cloning, impersonating, or commercially using any person's voice without proper rights or consent.

Source: k2-fsa/OmniVoice.