--:--:--
Kitten TTS
15M Parameters · Nano 0.1
15M
24 kHz
WASM
Model Engine
kitten-tts-nano-0.1 (INT8)
Checking cache…
Downloading model…
0%
Synthesize Speech
Input Prompt
0 / 2000
Welcome to the multi-model voice studio. This pipeline executes neural speech models entirely inside your browser using quantized WebAssembly.
Voice Persona
Loading voices…
Speed
1.00×
Generate Speech
0:00
Generation History
0 items
Clear All
No generations yet. Create your first audio on the left.