Kitten TTS Server

Generate Speech

Text to synthesize

Enter the text you want to convert to speech. For audiobooks, you can paste long chapters.

0 Characters

Split text into chunks

Select Voice:

Load Example Preset:

Loading presets...

Generation Parameters

Speed (1.0)

Output Format

MP3 is recommended for smaller file sizes (e.g., audiobooks).

Server Configuration

These settings are loaded from config.yaml via an API call. Restart the server to apply changes to Host, Port, Model, or Path settings if modified here or directly in the file.

Server Host

Server Port

TTS Device

Model Repository

Model Cache Path

Output Path

Audio Output Format

Audio Sample Rate

Resets settings to their defaults.

Tips & Tricks

For **Audiobooks**, use **MP3** format, enable **Split text**, and set a chunk size of ~250-500.
**KittenTTS** provides 8 high-quality voices: 4 male and 4 female expressions.
The model is ultra-lightweight (<25MB) and runs efficiently on both CPU and GPU.
Experiment with **Speed** to adjust playback rate (0.25x to 4.0x).
Check the /docs endpoint for API details.

Generate Speech

Tips & Tricks

Generation Quality Notice