MLX Audio Swift

Overview

MLX Audio Swift is a modular Swift SDK for audio processing with MLX on Apple silicon. It supports text to speech, speech to text, speaker diarisation and audio codecs, and downloads models automatically from the Hugging Face Hub. You import only the modules you need to keep app size down.

Features

• Text to speech, including streaming generation
• Speech to text
• Voice activity detection and speaker diarisation
• Audio codecs such as SNAC
• Voice selection for multi-voice models
• VoicesApp example built with SwiftUI

Requirements

• macOS 14 or later, or iOS 17 or later
• Apple silicon (M1 or later) recommended for best performance
• Xcode 15 or later
• Swift 5.9 or later

Install

1. Add the package to Package.swift and the products you need

   .package(url: "https://github.com/Blaizzy/mlx-audio-swift.git", branch: "main")