Kokoro

Detailed Description

Kokoro is an open-weight text-to-speech (TTS) model with 82 million parameters, striking a sweet spot between compact size and impressive output quality. It uses architectures like StyleTTS 2 and ISTFTNet, and employs a decoder-only design (no diffusion or encoder), which helps it remain lightweight while delivering high fidelity audio often comparable to much larger models. It's licensed under Apache-2.0, making it free for broad usage from personal projects to production deployments.