Model: KittenML/kitten-tts-nano-0.1
Features:
- High-quality text-to-speech synthesis
- Optimized for long text inputs through chunking
- Works without GPU acceleration
- Multiple voice options
- Adjustable speech speed (0.5x to 2.0x)
- 24kHz audio output
Usage:
- Enter or paste your text in the text box (long texts supported)
- Select a voice from the dropdown
- Adjust the speech speed if needed
- Click "Generate Speech" to create audio
Generated files are saved in a temporary directory with unique UUID filenames.
Long texts are automatically split into manageable chunks for efficient processing.