😻Kitten TTS Voice
Tiny 25MB AI voice — 8 voices, on-device. Free, private, no signup — files never leave your browser.
Kitten Nano downloads once (~25MB), then runs on-device. 8 voices, 0.5x–2x speed, 24 kHz WAV out.
Tiny model. Big voice.
Eight natural voices from a 25MB model that runs fully on your device. No upload, no signup, no watermark.
How to use Kitten TTS Voice
A tiny but mighty voice model that lives in your browser. Pick one of 8 voices, set the speed, and download a natural 24 kHz voice-over. The model downloads once (~25MB) and is cached — everything after that is instant and private.
- 1Type or paste up to 500 characters.
- 2Pick a voice (Bella, Jasper, Luna, Bruno, Rosie, Hugo, Kiki, Leo) and set speed.
- 3Hit Generate and download the WAV voice-over.
Use cases
What kitten tts voice does
- ✓Eight natural voices across female and male speakers.
- ✓Speed slider from 0.5x to 2x with per-voice tuning.
- ✓High-quality WAV download, upsampled to 48 kHz for editors.
- ✓Up to 500 characters per generation, with number and contraction handling.
- ✓Fully local ONNX: no uploads, no accounts, no watermarks.
Specs
- Speed
- Seconds per render, on-device
- Input
- Text up to 500 characters
- Output
- WAV voice-over (48 kHz)
- Privacy
- On-device ONNX, zero uploads
- Cost
- Free, unlimited, no signup
Frequently asked questions
Is my text sent to a server?
No. Kitten Nano runs 100% in your browser via ONNX. Your text never leaves your device.
Which voices are available?
Eight voices: Bella, Luna, Rosie and Kiki (female), Jasper, Bruno, Hugo and Leo (male).
Why does the first run take longer?
The voice model (~25MB) downloads once and is cached by your browser. Every run after that starts immediately.
What format is the download?
A 48 kHz WAV voice-over file you can drop into any video or podcast editor.