Modelpublic

mlx-community/kitten-tts-nano-0.8-fp16

sourceHugging Faceupdated 7mo agoView on Hugging Face

1likes17downloads

Model Card

mlx-community/kitten-tts-nano-0.8-fp16

This is the FP16 MLX conversion of KittenML/kitten-tts-nano-0.8.

Usage

bash

pip install -U mlx-audio

bash

python -m mlx_audio.tts.generate --model mlx-community/kitten-tts-nano-0.8-fp16 --text "This is a local MLX test voice." --voice "expr-voice-5-m"

Inference Notes

The MLX implementation includes small end-of-utterance smoothing to prevent abrupt cutoffs. You can override it with fade_out_ms=0 and tail_silence_ms=0 in Model.generate().

Original Model

Refer to the original model card for details: https://huggingface.co/KittenML/kitten-tts-nano-0.8