All models
voice-cloning

OmniVoice

Apache-2.0 (code) · CC-BY-NC (weights)

Voice cloning and voice design across a broad language range.

Voice cloning and voice design across a broad language range. The author reports 600+ languages; displayed codes are a subset. Code and weights have different terms: the pretrained weights are non-commercial.

Hear OmniVoice

Standardized samples are pending for this release. See the official sources below for the author’s demo.

OmniVoice · Default · Same three scripts across the directory.

Best for: Voice cloning and voice design across a broad language range.

Before you choose: The author reports 600+ languages; displayed codes are a subset. Code and weights have different terms: the pretrained weights are non-commercial.

No comparable hardware benchmark verified. Check the official setup for your device.

Details reviewed 2026-09-14. Hardware figures are estimates unless a benchmark is linked.

No samples yet

Every model in this directory is read against the same three scripts so voices can be compared honestly — OmniVoice’s samples just haven’t been generated yet.

Contribute samples on GitHub →

Run OmniVoice

pip install omnivoice
# Install the PyTorch build appropriate for your CUDA or Apple Silicon environment.

OmniVoice FAQ

Do I need a GPU to run OmniVoice?

We have not verified a hardware requirement for this release. Follow the official setup instructions.

Can OmniVoice clone voices?

Yes — OmniVoice supports voice cloning from reference audio.

What license is OmniVoice released under?

OmniVoice is released under the Apache-2.0 (code) · CC-BY-NC (weights) license. Always check the repository for the exact terms — some models license code and weights separately.

What languages does OmniVoice support?

OmniVoice supports English, Chinese, Japanese, Korean, German, French, Spanish, Italian, Portuguese, Russian, Arabic, Hindi.

Is there a hosted OmniVoice API?

OpenSpeech Cloud is accepting production-access interest for OmniVoice, but this model is not hosted in the beta. Use the official repository for current deployment options.