lexaloud is an open-source text-to-speech tool for Linux that uses the Kokoro-82M model to convert selected text into speech locally on the user's GPU. It prioritizes privacy and accessibility, making it ideal for Linux users seeking offline TTS capabilities.
lexaloud sits in PulseGate's Text to speech category. It focuses on enabling private, offline text-to-speech conversion on Linux desktops using local AI models. lexaloud is an open-source project aimed at linux users. lexaloud is open source under the MIT license. lexaloud is available on the web, the command line, and Linux.
It is developed by Gustavjiversen01, and it first shipped in 2026. The project is developed in the open on GitHub with 67 commits in the last 90 days. Among its 5 catalogued features are text-to-speech, hotkey activation, and GPU acceleration.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do