mlx-audio based local solution for text-to-speech (TTS), speech-to-text (STT), and speech-to-speech (STS), optimized for Apple Silicon (M1–M4).

All CLI commands use uvx --from mlx-audio — no Python installation needed.

how to use

Help

uvx --from mlx-audio mlx_audio.tts.generate --help
uvx --from mlx-audio mlx_audio.stt.generate --help
uvx --from mlx-audio mlx_audio.sts.generate --help

Text-to-Speech (TTS)