Text-to-Speech
Safetensors
Qwen3-TTS
MLX
mlx-audio
speech
speech generation
voice cloning
tts
8-bit precision
Instructions to use mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit --local-dir Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Download preprocessor_config.json from mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit: direct link, hf CLI and curl.
- Browser
- Download file 127 Bytes
-
https://huggingface.co/mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit/resolve/main/preprocessor_config.json
- Command line
-
hf download hf://mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit/preprocessor_config.json
-
curl -L -o preprocessor_config.json https://huggingface.co/mlx-community/Qwen3-TTS-12Hz-0.6B-CustomVoice-8bit/resolve/main/preprocessor_config.json
127 Bytes
| { | |
| "padding_side": "left", | |
| "padding_value": 0.0, | |
| "processor_class": "Qwen3TTSProcessor", | |
| "return_attention_mask": true | |
| } |