Small macOS application for Text-to-Speech using the the Kokoro TTS model, allowing high-quality offline TTS. Integrates as a macOS service to speak selected text quickly, optionally using a global hotkey.

Select any text in any application and select "Speak with Kokoro" from the context menu. Or press ⌘⇧P (Command+Shift+P) to speak it. You can also change the keyboard shortcut, for that go to System Settings → Keyboard → Keyboard Shortcuts → Services → Text → Speak with Kokoro. This item will only be created after you've started the app for the first time.

Alternatively, copy and paste text directly into the app's text field and press play. The generated audio can also be saved to a file.

• macOS 15.0+

Download the latest DMG from the Releases page.

Since the app is not signed, macOS will block it by default. To open it:

1. Right-click the app and select "Open"
2. Click "Open" in the dialog that appears

Or remove the quarantine attribute via Terminal:

xattr -cr /Applications/KokoroTTS.app

⚠️ Important: This repository uses Git LFS to store the large neural network model file (kokoro-v1_0.safetensors, ~315MB). You must have Git LFS installed and configured before cloning:

# Using Homebrew (macOS)
brew install git-lfs
git lfs install

Otherwise cloning and running the application is done as any other app:

1. Clone the repository (Git LFS will automatically download the model file):

   git clone https://github.com/kjyv/KokoroTTS.git
   cd KokoroTTS

   (if this doesn't download the model files because of LFS issues, you can also download the files manually from Github)

2. Verify model file: Ensure the model file was downloaded correctly:

   ls -la Resources/kokoro-v1_0.safetensors
   # Should show a file of approximately 315MB

3. Open in Xcode:

   open KokoroTTS.xcodeproj

4. Build and run the project in Xcode

• High-Quality TTS: Leverages the Kokoro neural TTS model for natural-sounding speech synthesis
• Multiple voices: Supports different voice options
• Faster than real-time generation: Fast audio generation with performance metrics
• MLX integration: Optimized for Apple Silicon using the MLX machine learning framework

This project uses Swift Package Manager with the following dependencies:

• Kokoro iOS: Kokoro TTS engine
• MLX: Apple's MLX machine learning framework
• MisakiSwift: Misaki G2P library
• MLXUtilsLibrary: For reading the .npz file for voice styles

This project is licensed under the Apache 2.0 License - see the LICENSE file for details.