Blaizzy/mlx-audio
A text-to-speech, speech-to-text, and speech-to-speech library built on Apple's MLX framework for efficient inference on Apple Silicon.
Velocity · 7d
+13
★ / day
Trend
→steady
star history
MLX-Audio provides speech synthesis and recognition capabilities through multiple model architectures optimized for Apple Silicon. It supports multilingual TTS and STT with features like voice cloning, adjustable speech speed, and quantization options (3-bit through 8-bit). The library exposes an OpenAI-compatible REST API and includes an interactive web interface with 3D audio visualization, targeting developers building speech-enabled applications on Apple hardware.