Out Loud is a free, open-source AI text-to-speech app that runs 100% offline. Nothing you read or type ever leaves your device — no cloud, no accounts, no tracking. Get 50+ natural voices across 8 languages (English, Japanese, Chinese, Spanish, Hindi, Italian, Portuguese, and more) on macOS, Windows, and Linux, plus a Chrome extension that reads any webpage, PDF, or email aloud with one click.
MIT licensed and free forever — audit it, fork it, improve it. A genuine alternative to subscription TTS services, with no fees, ever.
Download v2.0.0: https://www.out-loud.io/#download Star on GitHub: https://github.com/light-cloud-com/out-loud
This seems to be a wrapper over Kokoro which is an Apache-licenced TTS model and library which has been out for over a year. That model lists about 10% of its approx 1000-hour training data but also says that all of its training data was CC, synthetic (by way of closed source TTs), or otherwise permissively-licensed.
huggingface kokoro