About kokoro
Kokoro is an open-source text-to-speech (TTS) model with 82 million parameters, designed for those seeking a lightweight yet high-quality solution for voice synthesis. It offers comparable performance to larger models while being faster and more cost-efficient. With Apache-licensed weights, Kokoro is suitable for deployment in various environments, from production to personal projects. The model leverages the misaki G2P library for enhanced functionality.
kokoro — FAQ
What is kokoro?+
kokoro is a voice AI product — https://hf.co/hexgrad/Kokoro-82M
What does kokoro do?+
kokoro works in Text-to-Speech (TTS) — https://hf.co/hexgrad/Kokoro-82M.
Is kokoro open source?+
Yes, kokoro is open source (Apache-2.0 license). The source is on https://github.com/hexgrad.
