Open Source Swift Speech Recognition Software

WhisperKit is a Swift package that integrates OpenAI's popular Whisper speech recognition model with Apple's CoreML framework for efficient, local inference on Apple devices. Whisper has pulled the future forward when fast, free and virtually error-free translation and transcription will be ubiquitous. It inspired numerous developers to improve and deploy it with minimal friction and maximum performance. We founded Argmax in November 2023 to empower developers and enterprises everywhere to deploy commercial-scale inference workloads on user devices. The fast-growing need for Whisper inference in production convinced us to take it on as our first project.

Yap is a free, open-source voice dictation application for macOS that converts speech into text entirely on the user's device. Built with native Swift, it uses Apple's SpeechAnalyzer and SpeechTranscriber APIs to deliver fast, real-time transcription without cloud services, accounts, or API keys. Users can activate dictation through customizable global keyboard shortcuts and automatically insert recognized text into virtually any application. A floating interface displays live audio waveforms and partial transcriptions while recording. The software maintains a searchable local history where previous transcripts can be copied or deleted. It also supports microphone switching, optional startup at login, and flexible menu bar visibility. Designed for Apple silicon Macs running macOS 26 Tahoe or later, Yap emphasizes privacy, lightweight performance, and straightforward voice-to-text functionality.