{"id":"kokoro","name":"Kokoro","maker":"hexgrad","url":"https://github.com/hexgrad/kokoro","repo":"hexgrad/kokoro","package":"pypi:kokoro","summary":"A small open text-to-speech model with a Python inference package, released with Apache licensed weights.","details":"An 82 million parameter model that runs locally on CPU or GPU and supports several voices and languages. Its inference library is Apache 2.0 licensed and its weights are published on Hugging Face.","open_source":true,"hosted":false,"verified":"2026-11-15","category":"voice","category_name":"Voice agents and realtime speech","page":"https://modelmoot.com/tools/kokoro","reviewed":"2026-11-15","checked":{"at":"2026-11-15T14:03:44.997Z","address_answers":true,"repository":{"at":"2026-11-16T01:30:22.397Z","archived":false,"licence":"Apache-2.0","language":"JavaScript","last_change":"2025-08-06T22:28:53.000Z","latest_release":null}},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}