Argmax OSS Swift (WhisperKit)

Overview

The Argmax Open-Source SDK is a collection of on-device inference frameworks for Swift. It includes WhisperKit for speech to text with OpenAI Whisper, SpeakerKit for speaker diarisation with Pyannote and TTSKit for text to speech with Qwen-TTS. A CLI also runs a local server compatible with the OpenAI Audio API.

Features

• WhisperKit transcribes local audio files in a few lines of Swift
• SpeakerKit for speaker diarisation
• TTSKit for text to speech
• Memory-efficient loading for large audio files
• Swift CLI for testing outside Xcode
• Local server with OpenAI-style transcription endpoints

Requirements

• macOS 14.0 or later
• Xcode 16.0 or later

Install

1. Add the package in Xcode (File > Add Package Dependencies) or Package.swift

   .package(url: "https://github.com/argmaxinc/argmax-oss-swift.git", from: "0.9.0")

2. Or install the command line app

   brew install whisperkit-cli

Example

Initialise WhisperKit and call transcribe(audioPath:) on a local audio file to get its text.