Text-to-Speech
Safetensors
MLX
mlx-audio
voxtral_tts
mistral-common
speech
speech generation
voice cloning
tts
Instructions to use AITRADER/Voxtral-4B-TTS-2603-bf16 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use AITRADER/Voxtral-4B-TTS-2603-bf16 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Voxtral-4B-TTS-2603-bf16 AITRADER/Voxtral-4B-TTS-2603-bf16
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
AITRADER/Voxtral-4B-TTS-2603-bf16
This model was converted to MLX format from mistralai/Voxtral-4B-TTS-2603 using mlx-audio version 0.4.1.
Refer to the original model card for more details on the model.
Use with mlx-audio
pip install -U mlx-audio
CLI Example:
python -m mlx_audio.tts.generate --model AITRADER/Voxtral-4B-TTS-2603-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("AITRADER/Voxtral-4B-TTS-2603-bf16")
generate_audio(
model=model,
text="Hello, this is a test.",
ref_audio="path_to_audio.wav",
file_prefix="test_audio",
)
- Downloads last month
- 46
Model size
4B params
Tensor type
BF16
·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for AITRADER/Voxtral-4B-TTS-2603-bf16
Base model
mistralai/Ministral-3-3B-Base-2512