--- tags: - mlx - text-to-speech - kitten-tts - kitten_tts --- # mlx-community/kitten-tts-micro-0.8-5bit This is the **INT5 (MLX 5-bit)** MLX conversion of `KittenML/kitten-tts-micro-0.8`. ## Usage ```bash pip install -U mlx-audio ``` ```bash python -m mlx_audio.tts.generate --model mlx-community/kitten-tts-micro-0.8-5bit --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-micro-0.8