0 / 5,000 characters
First use downloads 63MB - after that it's cached forever.
How it works
100% on-device: Voice models are downloaded once, then cached in your browser's Origin Private File System. No text or audio is ever sent to any server.
Powered by Piper TTS - a fast neural TTS engine from the Rhasspy project. Voice models are open-source (MIT) and hosted on Hugging Face.
Works on every device: Chrome, Safari, Firefox, Edge - desktop and mobile. No microphone or special permissions required.
Your text is processed locally on your device. OptiPix never sees what you type.
Powered by OptiPix Text to Speech - free, private, in-browser