metadata
license: llama3.2
library_name: mlx-audio
language:
- en
tags:
- mlx
- tts
- text-to-speech
- speech-synthesis
- tada
- apple-silicon
- mlx
- text-to-speech
- speech
- speech generation
- voice cloning
- tts
- mlx-audio
pipeline_tag: text-to-speech
base_model: meta-llama/Llama-3.2-1B
arxiv: 2602.23068
mlx-community/tada-tts
This model was converted to MLX format from HumeAI/mlx-tada-1b using mlx-audio version 0.2.8.
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 mlx-community/tada-tts --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("mlx-community/tada-tts")
generate_audio(
model=model,
text="Hello, this is a test.",
ref_audio="path_to_audio.wav",
file_prefix="test_audio",
)