> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/argmaxinc/WhisperKit/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> Version history and release notes for WhisperKit

## Overview

WhisperKit follows [semantic versioning](https://semver.org/). This page documents major changes, new features, bug fixes, and breaking changes across versions.

<Note>
  For detailed commit history, see [GitHub Releases](https://github.com/argmaxinc/WhisperKit/releases).
</Note>

## Version 0.9.0

<Card title="Latest Release" icon="star">
  Current stable version with TTSKit integration and local server
</Card>

### Release Date

**Released**: 2024

### Major Features

<AccordionGroup>
  <Accordion title="TTSKit - Text-to-Speech Framework" icon="volume-high">
    New text-to-speech capabilities:

    **Features:**

    * On-device TTS using Qwen3 models
    * Two model sizes: 0.6B (iOS/macOS) and 1.7B (macOS)
    * Real-time streaming playback
    * 9 voices in 10 languages
    * Style instructions (1.7B model)
    * Audio export (WAV, M4A)

    **Usage:**

    ```swift theme={null}
    import TTSKit

    let tts = try await TTSKit()
    try await tts.play(text: "Hello from TTSKit!")
    ```

    See [TTSKit Guide](/ttskit/overview) for details.
  </Accordion>

  <Accordion title="WhisperKit Local Server" icon="server">
    OpenAI-compatible HTTP server:

    **Features:**

    * Implements OpenAI Audio API
    * Server-Sent Events (SSE) streaming
    * Compatible with OpenAI SDKs
    * Auto-generated OpenAPI specification
    * Example clients (Python, Swift, curl)

    **Usage:**

    ```bash theme={null}
    BUILD_ALL=1 swift run whisperkit-cli serve
    ```

    **API Endpoints:**

    * `POST /v1/audio/transcriptions`
    * `POST /v1/audio/translations`

    See [Local Server Guide](/advanced/local-server) for details.
  </Accordion>
</AccordionGroup>

### Improvements

* Enhanced streaming transcription performance
* Better memory management for large models
* Improved model loading and caching
* CLI enhancements with new commands
* Updated model repository structure
* Better error messages and debugging

### Bug Fixes

* Fixed memory leaks in long-running transcription
* Resolved model download issues on slow connections
* Fixed timestamp alignment in certain edge cases
* Improved handling of corrupted audio files
* Fixed crashes when switching models rapidly

### Dependencies

* Swift 5.9+
* macOS 14.0+ (WhisperKit), 15.0+ (TTSKit)
* iOS 16.0+ (WhisperKit), 18.0+ (TTSKit)
* Xcode 16.0+

### Breaking Changes

<Warning>
  No breaking changes in this release. All 0.8.x code remains compatible.
</Warning>

## Version 0.8.0

### Release Date

**Released**: 2024

### Major Features

<AccordionGroup>
  <Accordion title="Unified Configuration API" icon="gear">
    Centralized configuration through `WhisperKitConfig`:

    ```swift theme={null}
    let config = WhisperKitConfig(
        model: "large-v3",
        modelRepo: "argmaxinc/whisperkit-coreml",
        computeUnits: .cpuAndNeuralEngine,
        verbose: true
    )
    let pipe = try await WhisperKit(config)
    ```
  </Accordion>

  <Accordion title="Enhanced Model Selection" icon="filter">
    Support for glob patterns in model selection:

    ```swift theme={null}
    // Matches distil-whisper_distil-large-v3
    let pipe = try await WhisperKit(
        WhisperKitConfig(model: "distil*large-v3")
    )
    ```
  </Accordion>

  <Accordion title="Improved Streaming" icon="stream">
    Better real-time transcription with:

    * Lower latency
    * More accurate intermediate results
    * Better VAD integration
    * Reduced memory usage
  </Accordion>
</AccordionGroup>

### Improvements

* Faster model loading from cache
* Better error handling and recovery
* Improved voice activity detection
* Enhanced word timestamp accuracy
* Better multilingual support
* Reduced peak memory usage

### Bug Fixes

* Fixed race conditions in streaming mode
* Resolved model cache corruption issues
* Fixed timestamp drift in long audio
* Improved handling of silence
* Fixed crashes on certain audio formats

### Deprecations

<Warning>
  **Deprecated:**

  * Direct initializer parameters (use `WhisperKitConfig`)
  * `modelFolder` parameter (use `model` in config)
</Warning>

## Version 0.7.0

### Release Date

**Released**: 2023

### Major Features

* Swift CLI tool for command-line transcription
* Enhanced model repository on HuggingFace
* Support for custom model repositories
* Improved benchmark suite
* Better documentation and examples

### Improvements

* 20% faster transcription on M1 Macs
* Reduced model download size
* Better progress reporting
* Enhanced example applications
* Improved API documentation

### Bug Fixes

* Fixed model loading on iOS devices
* Resolved audio buffer overflow issues
* Fixed language detection accuracy
* Improved error messages

## Version 0.6.0

### Release Date

**Released**: 2023

### Major Features

* Support for Whisper large-v3 models
* Distilled model support
* Voice activity detection integration
* Real-time streaming transcription
* Word-level timestamps

### Improvements

* 30% faster model loading
* Better memory efficiency
* Improved accuracy on noisy audio
* Enhanced iOS support

## Earlier Versions

<Accordion title="Version 0.5.0 and earlier">
  ### Version 0.5.0

  * Initial public release
  * Support for Whisper base, small, medium models
  * iOS and macOS support
  * Basic transcription API

  ### Version 0.4.0 (Beta)

  * Beta release for early adopters
  * CoreML model optimization
  * Basic streaming support

  ### Version 0.3.0 (Alpha)

  * Alpha release for testing
  * Proof of concept implementation
</Accordion>

## Upcoming Features

<Info>
  These features are planned for future releases. Follow development on [GitHub](https://github.com/argmaxinc/WhisperKit).
</Info>

### Version 1.0 (Planned)

<CardGroup cols={2}>
  <Card title="Stable API" icon="lock">
    API stability guarantees
  </Card>

  <Card title="Enhanced Models" icon="brain">
    New optimized model variants
  </Card>

  <Card title="More Languages" icon="language">
    Additional language support
  </Card>

  <Card title="Better Diarization" icon="users">
    Improved speaker detection
  </Card>
</CardGroup>

### Future Roadmap

* **Enhanced Streaming**: Lower latency, better accuracy
* **More TTS Voices**: Additional voice options
* **Custom Wake Words**: On-device wake word detection
* **Noise Reduction**: Advanced audio preprocessing
* **Batch Processing**: Efficient multi-file transcription
* **Cloud Sync**: Optional cloud backup and sync

## Version Support

<Tabs>
  <Tab title="Current">
    ### Active Support

    **Version 0.9.x**

    * ✅ Bug fixes
    * ✅ Security updates
    * ✅ New features
    * ✅ Community support

    **Recommended**: Use the latest 0.9.x release.
  </Tab>

  <Tab title="Maintenance">
    ### Maintenance Mode

    **Version 0.8.x**

    * ✅ Critical bug fixes only
    * ✅ Security updates
    * ❌ No new features

    **Version 0.7.x**

    * ⚠️ Security updates only
    * ❌ No bug fixes
    * ❌ No new features
  </Tab>

  <Tab title="End of Life">
    ### No Longer Supported

    **Version 0.6.x and earlier**

    * ❌ No support
    * ❌ No updates
    * ⚠️ Security vulnerabilities

    **Action**: Migrate to 0.9.x immediately.
  </Tab>
</Tabs>

## Migration Guides

<CardGroup cols={2}>
  <Card title="Migrate to 0.9.x" icon="arrow-up" href="/resources/migration-guide">
    Upgrade from any previous version
  </Card>

  <Card title="Breaking Changes" icon="triangle-exclamation">
    Review breaking changes by version
  </Card>
</CardGroup>

## Reporting Issues

Found a bug or have a feature request?

<Steps>
  <Step title="Check Existing Issues">
    Search [GitHub Issues](https://github.com/argmaxinc/WhisperKit/issues) to avoid duplicates.
  </Step>

  <Step title="Gather Information">
    Collect:

    * WhisperKit version
    * Device and OS version
    * Steps to reproduce
    * Expected vs actual behavior
  </Step>

  <Step title="Create Issue">
    [Create a new issue](https://github.com/argmaxinc/WhisperKit/issues/new) with details.
  </Step>
</Steps>

## Release Notes Format

Each release includes:

* **Features**: New capabilities and functionality
* **Improvements**: Performance and quality enhancements
* **Bug Fixes**: Resolved issues
* **Breaking Changes**: API changes requiring code updates
* **Deprecations**: Features scheduled for removal
* **Migration Guide**: Steps to update from previous versions

## Staying Updated

<CardGroup cols={2}>
  <Card title="GitHub" icon="github" href="https://github.com/argmaxinc/WhisperKit">
    Watch the repository for releases
  </Card>

  <Card title="Discord" icon="discord" href="https://discord.gg/G5F5GZGecC">
    Join for release announcements
  </Card>

  <Card title="RSS Feed" icon="rss" href="https://github.com/argmaxinc/WhisperKit/releases.atom">
    Subscribe to release feed
  </Card>

  <Card title="Twitter" icon="twitter" href="https://twitter.com/argmaxinc">
    Follow for updates
  </Card>
</CardGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="Migration Guide" icon="arrows-turn-to-dots" href="/resources/migration-guide">
    Upgrade to the latest version
  </Card>

  <Card title="FAQ" icon="circle-question" href="/resources/faq">
    Common questions answered
  </Card>

  <Card title="Contributing" icon="code-pull-request" href="/resources/contributing">
    Help shape future releases
  </Card>

  <Card title="Benchmarks" icon="chart-line" href="/resources/benchmarks">
    Compare versions
  </Card>
</CardGroup>