OmniVoice-bf16

theoracleguy/OmniVoice-bf16

This model was converted to MLX format from k2-fsa/OmniVoice using mlx-audio.

Refer to the original model card for more details on the model.

Use with OpenVox

This model can also be used with OpenVox, a desktop application for running compatible AI voice and text-to-speech models locally through a graphical interface.

After the required model files are downloaded, compatible workflows can run locally and can also be accessed through OpenVox API and MCP integrations.

Available features depend on the capabilities of the selected model. OpenVox is a third-party application and is not affiliated with or endorsed by the original model authors or maintainers.

Use with mlx-audio

pip install -U mlx-audio

CLI Example:

python -m mlx_audio.tts.generate --model theoracleguy/OmniVoice-bf16 --text "Hello, this is a test."

Python Example:

from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio
model = load_model("theoracleguy/OmniVoice-bf16")
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    file_prefix="test_audio",
)