Kokoro is a high-quality, lightweight text-to-speech model that has become one of the most popular open-source TTS options due to its exceptional voice quality and fast inference speed. With only 82 million parameters, Kokoro delivers voices that rival much larger commercial TTS systems while running efficiently on consumer hardware. The model supports multiple English voices with natural prosody and can be fine-tuned for custom voices. Kokoro is available on Hugging Face and can be run locally, making it ideal for privacy-conscious applications.