MLX Audio

Text-to-speech, speech-to-text and audio models under one MLX package.

When to use it

Use this when you want both directions of speech from one dependency instead of stitching separate Whisper and TTS repos together.

A batched, quantized Whisper reimplementation chasing raw transcription speed.

Prompt-controllable speech: describe the voice you want in plain English.

Speech in, speech out, skipping the ASR-LLM-TTS relay race.