Downloads · 30 days
28
7% of all-time downloads
Voxtral-4B-TTS-2603-mxfp8
AITRADER/Voxtral-4B-TTS-2603-mxfp8
Voxtral-4B-TTS-2603-mxfp8 is a text-to-speech model from AITRADER. Use it when you need text read aloud. It is set up for mlx-audio. The card lists the license as cc-by-nc-4.0.
This model was converted to MLX format from mistralai/Voxtral-4B-TTS-2603 using mlx-audio version 0.4.1.
All-time downloads
406
Public
Parameters
4B
4.7 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors4.7 GB · 100%
Parameter types
How the weights are stored.
U323.4B · 85%
Base models
Model card
From the Hugging Face model README
AITRADER/Voxtral-4B-TTS-2603-mxfp8
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-mxfp8 --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-mxfp8")
generate_audio(
model=model,
text="Hello, this is a test.",
ref_audio="path_to_audio.wav",
file_prefix="test_audio",
)
- Task
- Text-to-Speech
- Library
- mlx-audio
- Type
- voxtral_tts
- License
- cc-by-nc-4.0
- Languages
- en, fr, es, pt, it, nl
- Created
- Mar 27, 2026
- Updated
- Mar 27, 2026