Text-to-Speech (TTS)
π️
Text-To-Speech (TTS)
Core Engine V2
Initializing...
Loading library
Input Text
0 / 2000
Voice Model
Speed
1.0x
Neural Waveform
0:00
0:00
Privacy & Performance
All synthesis occurs locally in your browser. No text or audio is uploaded to any server.
First load downloads ~85 MB of model weights, then caches them. Subsequent loads are instant.
Debug Log