OmniVoice in MLX (4bit). For mlx-audio on Apple Silicon.

Usage

pip install mlx-audio
python -m mlx_audio.tts.generate \
  --model commandeaw/OmniVoice-MLX-4bit \
  --text "สวัสดีค่ะ ยินดีต้อนรับ" \
  --lang_code th \
  --ref_audio reference.wav

--ref_audio is optional (zero-shot voice cloning); drop it for the default voice.

Size

variant repo vs base (fp32)
bf16 1.6 GB -50%
8bit 1.1 GB -68%
4bit 0.75 GB -77%
Downloads last month
130
Safetensors
Model size
95.8M params
Tensor type
BF16
·
U32
·
MLX
Hardware compatibility
Log In to add your hardware

Quantized

Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for commandeaw/OmniVoice-MLX-4bit

Finetuned
Qwen/Qwen3-0.6B
Finetuned
k2-fsa/OmniVoice
Quantized
(11)
this model