# WhisperKit

## Docs

- [CLI Usage](https://mintlify.wiki/argmaxinc/WhisperKit/advanced/cli-usage.md): Command-line interface for transcription, translation, and streaming
- [Custom Models](https://mintlify.wiki/argmaxinc/WhisperKit/advanced/custom-models.md): Create, train, and deploy custom Whisper models with WhisperKit
- [Local Server](https://mintlify.wiki/argmaxinc/WhisperKit/advanced/local-server.md): Run WhisperKit as an OpenAI-compatible local transcription server
- [Memory Management](https://mintlify.wiki/argmaxinc/WhisperKit/advanced/memory-management.md): Optimize memory usage for WhisperKit models on resource-constrained devices
- [Performance Optimization](https://mintlify.wiki/argmaxinc/WhisperKit/advanced/performance-optimization.md): Optimize transcription speed, memory usage, and quality with WhisperKit
- [ModelComputeOptions](https://mintlify.wiki/argmaxinc/WhisperKit/api/core/model-compute-options.md): Configure compute units for WhisperKit model components
- [ModelState](https://mintlify.wiki/argmaxinc/WhisperKit/api/core/model-state.md): Lifecycle state of a loaded ML model pipeline
- [Core Protocols](https://mintlify.wiki/argmaxinc/WhisperKit/api/core/protocols.md): Protocol definitions for WhisperKit's modular pipeline components
- [AudioOutput](https://mintlify.wiki/argmaxinc/WhisperKit/api/ttskit/audio-output.md): Audio export and real-time streaming playback handler
- [GenerationOptions](https://mintlify.wiki/argmaxinc/WhisperKit/api/ttskit/generation-options.md): Options that control the speech synthesis pipeline
- [TTSKit](https://mintlify.wiki/argmaxinc/WhisperKit/api/ttskit/ttskit-class.md): Main TTS orchestrator class for text-to-speech synthesis
- [TTSKitConfig](https://mintlify.wiki/argmaxinc/WhisperKit/api/ttskit/ttskit-config.md): Configuration class for initializing TTSKit instances
- [AudioProcessor](https://mintlify.wiki/argmaxinc/WhisperKit/api/whisperkit/audio-processor.md): Audio processing and recording functionality for WhisperKit
- [TranscriptionResult](https://mintlify.wiki/argmaxinc/WhisperKit/api/whisperkit/transcription-result.md): Result object containing transcribed text, segments, and metadata
- [VoiceActivityDetector](https://mintlify.wiki/argmaxinc/WhisperKit/api/whisperkit/voice-activity-detector.md): Base class for voice activity detection in audio streams
- [WhisperKit](https://mintlify.wiki/argmaxinc/WhisperKit/api/whisperkit/whisperkit-class.md): Main class for speech recognition with WhisperKit
- [WhisperKitConfig](https://mintlify.wiki/argmaxinc/WhisperKit/api/whisperkit/whisperkit-config.md): Configuration object for initializing WhisperKit
- [Basic Transcription](https://mintlify.wiki/argmaxinc/WhisperKit/examples/basic-transcription.md): Learn how to transcribe audio files with WhisperKit
- [Local Server & Clients](https://mintlify.wiki/argmaxinc/WhisperKit/examples/local-server-clients.md): Set up a local transcription server with client examples
- [Real-Time Streaming](https://mintlify.wiki/argmaxinc/WhisperKit/examples/real-time-streaming.md): Transcribe audio in real-time from a microphone
- [Text-to-Speech with TTSKit](https://mintlify.wiki/argmaxinc/WhisperKit/examples/text-to-speech.md): Generate natural speech from text on-device
- [Installation](https://mintlify.wiki/argmaxinc/WhisperKit/installation.md): Add WhisperKit and TTSKit to your Swift project
- [Introduction](https://mintlify.wiki/argmaxinc/WhisperKit/introduction.md): On-device speech recognition and text-to-speech for Apple Silicon
- [Quick Start](https://mintlify.wiki/argmaxinc/WhisperKit/quickstart.md): Get started with WhisperKit speech recognition and TTSKit text-to-speech in minutes
- [Benchmarks](https://mintlify.wiki/argmaxinc/WhisperKit/resources/benchmarks.md): Run performance benchmarks for WhisperKit models across different devices
- [Changelog](https://mintlify.wiki/argmaxinc/WhisperKit/resources/changelog.md): Version history and release notes for WhisperKit
- [Contributing](https://mintlify.wiki/argmaxinc/WhisperKit/resources/contributing.md): Guidelines for contributing to WhisperKit
- [FAQ](https://mintlify.wiki/argmaxinc/WhisperKit/resources/faq.md): Frequently asked questions about WhisperKit and TTSKit
- [Migration Guide](https://mintlify.wiki/argmaxinc/WhisperKit/resources/migration-guide.md): Upgrade to the latest version of WhisperKit
- [Model Catalog](https://mintlify.wiki/argmaxinc/WhisperKit/resources/model-catalog.md): Available Whisper and TTS models for WhisperKit and TTSKit
- [Supported Devices](https://mintlify.wiki/argmaxinc/WhisperKit/resources/supported-devices.md): Device compatibility and requirements for WhisperKit and TTSKit
- [Configuration](https://mintlify.wiki/argmaxinc/WhisperKit/ttskit/configuration.md): Configure TTSKit with compute units, model variants, and component overrides
- [Speech Generation](https://mintlify.wiki/argmaxinc/WhisperKit/ttskit/generation.md): Generate speech from text with chunking, sampling, and concurrent generation
- [Overview](https://mintlify.wiki/argmaxinc/WhisperKit/ttskit/overview.md): On-device text-to-speech with Qwen3 TTS models on Apple silicon
- [Real-Time Playback](https://mintlify.wiki/argmaxinc/WhisperKit/ttskit/playback.md): Stream audio to device speakers with adaptive buffering strategies
- [Voices & Languages](https://mintlify.wiki/argmaxinc/WhisperKit/ttskit/voices-and-languages.md): Available voices, languages, and voice selection for Qwen3 TTS models
- [Configuration](https://mintlify.wiki/argmaxinc/WhisperKit/whisperkit/configuration.md): Advanced configuration options for WhisperKit
- [Model Selection](https://mintlify.wiki/argmaxinc/WhisperKit/whisperkit/model-selection.md): Choose and download the right Whisper model for your application
- [WhisperKit Overview](https://mintlify.wiki/argmaxinc/WhisperKit/whisperkit/overview.md): Introduction to WhisperKit - On-device speech recognition powered by OpenAI Whisper
- [Streaming Transcription](https://mintlify.wiki/argmaxinc/WhisperKit/whisperkit/streaming.md): Real-time audio transcription from microphone input
- [Audio Transcription](https://mintlify.wiki/argmaxinc/WhisperKit/whisperkit/transcription.md): Transcribe audio files and arrays with WhisperKit
- [Voice Activity Detection](https://mintlify.wiki/argmaxinc/WhisperKit/whisperkit/voice-activity-detection.md): Detect speech segments and optimize transcription with VAD