On-Device Speech AI for Apple Silicon

Deploy state-of-the-art speech-to-text and text-to-speech models directly on iOS, macOS, watchOS, and visionOS with real-time streaming, voice activity detection, and more.

Get Started API Reference View on GitHub

Quick start

Get up and running with WhisperKit in minutes

Add WhisperKit to your project by adding the package dependency in Xcode or your `Package.swift` file: ```swift Package.swift theme={null} dependencies: [ .package(url: "https://github.com/argmaxinc/WhisperKit.git", from: "0.9.0") ] ``` Then add the products you need as target dependencies: ```swift theme={null} .target( name: "YourApp", dependencies: [ "WhisperKit", // speech-to-text "TTSKit", // text-to-speech ] ) ``` Import and initialize WhisperKit in your Swift code. The framework automatically downloads the recommended model for your device: ```swift theme={null} import WhisperKit Task { let pipe = try? await WhisperKit() print("WhisperKit initialized and ready") } ``` WhisperKit automatically selects and downloads the optimal model for your device. For custom model selection, see the [model selection guide](/whisperkit/model-selection). Use the `transcribe` method to convert audio files to text: ```swift theme={null} let transcription = try? await pipe!.transcribe( audioPath: "path/to/audio.wav" )?.text print(transcription) ``` WhisperKit supports multiple audio formats including WAV, MP3, M4A, and FLAC. For text-to-speech, import TTSKit and generate audio from text: ```swift theme={null} import TTSKit Task { let tts = try await TTSKit() let result = try await tts.generate(text: "Hello from TTSKit!") // Or play directly with streaming try await tts.play(text: "Hello from TTSKit!") } ```

Core features

Everything you need for on-device speech AI

Deploy Whisper models on-device with real-time streaming transcription and word-level timestamps Generate natural speech with multiple voices and languages using Qwen3 TTS models Automatically detect speech segments with built-in energy-based VAD Run on iOS, macOS, watchOS, and visionOS with optimized Core ML models OpenAI-compatible API for local speech processing with streaming support Automatic model downloading from HuggingFace with custom model support

Explore by topic

Deep dive into WhisperKit capabilities

Real-Time Streaming

Stream audio from microphone with live transcription using AudioStreamTranscriber

Learn more

Streaming Playback

Real-time audio streaming with intelligent buffering strategies for smooth playback

Learn more

Custom Models

Fine-tune and deploy your own Whisper models with whisperkittools

Learn more

Performance Optimization

Optimize inference speed and memory usage with compute unit selection

Learn more

Resources

Additional resources to help you succeed

Browse available Whisper and TTS models with performance benchmarks View performance metrics across different Apple Silicon devices Learn how to contribute to WhisperKit development Join the community for support and discussions

Ready to get started?

Build powerful on-device speech applications with WhisperKit today

View Quickstart View Examples