mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16

This model was converted to MLX format from Qwen/Qwen3-TTS-12Hz-0.6B-Base using mlx-audio version 0.3.0rc1.

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

Use with mlx-audio

pip install -U mlx-audio

CLI Example

# Using a predefined speaker
python -m mlx_audio.tts.generate --model mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16 --text "Hello, this is a test." --voice Chelsie

# Using reference audio for voice cloning
python -m mlx_audio.tts.generate --model mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16 --text "Hello, this is a test." --ref_audio path_to_audio.wav --ref_text "Transcript of the reference audio."

Python Example

from mlx_audio.tts.utils import load_model
from mlx_audio.tts.generate import generate_audio

model = load_model("mlx-community/Qwen3-TTS-12Hz-0.6B-Base-bf16")

# Using a predefined speaker
generate_audio(
    model=model,
    text="Hello, this is a test.",
    voice="Chelsie",
    file_prefix="test_audio",
)

# Using reference audio for voice cloning
generate_audio(
    model=model,
    text="Hello, this is a test.",
    ref_audio="path_to_audio.wav",
    ref_text="Transcript of the reference audio.",
    file_prefix="test_audio",
)

Available Speakers

Chelsie, Ethan, Serena, Vivian, Ryan, Aiden, Eric, Dylan