Introduction to Kokori
Kokori is a powerful macOS application designed to transform text into speech with ease. Built on the Kokoro TTS engine, it provides a local API server and desktop interface that allows users to generate high-quality audio directly from their Mac. With over 50 voices across multiple languages, Kokori offers flexibility and control for developers, creators, and anyone looking for a reliable text-to-speech solution.
The app is optimized for seamless integration with the macOS menubar, making it easy to access and use without interrupting your workflow. It runs entirely offline, ensuring privacy and performance without the need for internet connectivity or cloud services. Whether you're testing applications, creating content, or simply converting text to speech, Kokori delivers fast, accurate, and customizable results.
Takeaways
- High-quality text-to-speech with over 50 voices
- Local API server for offline use
- Seamless macOS menubar integration
- No quotas or restrictions on text generation
- Detailed logging and audio history support
- Simple REST API for developers
- Supports multiple languages including English, Japanese, Chinese, Spanish, French, Hindi, and more
How Kokori Works
Kokori operates as both a desktop application and a local API server. Users can interact with it through the intuitive GUI or via a RESTful API endpoint (http://localhost:5002/tts). By sending a JSON payload with parameters like text, voice, and speed, users can generate audio files instantly. The app handles all processing locally, ensuring fast response times and complete data privacy.
Core Benefits and Applications
Kokori is ideal for developers who want to test text-to-speech functionality without incurring API costs. It's also useful for content creators who need to generate voiceovers or audiobooks. Additionally, its offline nature makes it suitable for environments where internet access is limited or restricted. The ability to choose from a wide range of voices allows users to match the tone and style of their projects effectively.
Available Voices
| Language | Voice ID | Description |
|---|---|---|
| American English (Female) | af_heart | High Quality (A) |
| American English (Female) | af_bella | High Quality (A-) |
| American English (Female) | af_nicole | Medium Quality (B-) |
| American English (Male) | am_fenrir | Medium Quality (C+) |
| British English (Female) | bf_alice | High Quality (A) |
| British English (Male) | bm_daniel | Medium Quality (B) |
| Japanese (Female) | jf_alpha | - |
| Mandarin Chinese (Female) | zf_xiaobei | - |
| Spanish (Female) | ef_dora | - |
| French (Female) | ff_siwis | - |
| Hindi (Female) | hf_alpha | - |
| Italian (Female) | if_sara | - |
| Brazilian Portuguese (Female) | pf_dora | - |
