Convert text to speech in two clicks
Kokoro is an AI-powered tool designed to generate audiobooks and convert any text into speech with just two clicks. It leverages advanced machine learning models for text-to-speech conversion, enabling users to seamlessly transform their written content into audio format. The tool requires an initial download of a 300 MB text-to-speech model (Kokoro-82M-v1.0-ONNX), which is cached after the first use, ensuring that subsequent conversions are efficient and quick.