VoxWild

What it does

VoxWild is a Windows desktop app for AI text-to-speech that runs offline. It includes 13 voices, voice cloning from a 6-second sample, AI enhancement, and a batch queue. Fast mode is free forever, while Pro costs $12 per month or $89 once.

VoxWild is a Windows desktop app that turns text into speech on your own machine. The page says it runs 100% offline, with no cloud, no account, and no character caps. It ships with 13 voices and can clone a voice from a 6-second sample. A batch queue and AI enhancement are also listed. Fast mode is free forever. Pro costs $12 per month or $89 once, and the lifetime option includes future updates. The app uses the open-source Kokoro and Chatterbox speech models. The installer is unsigned, so SmartScreen warns on first run. The download is hosted on GitHub Releases, and the page says you can inspect the Python code. Commercial use is allowed on every tier, but Chatterbox output carries an inaudible watermark, and the EULA requires that you only clone voices you have rights to clone. The page does not state whether an API is available. It also does not say whether the app itself is open source, only that it wraps open-source models.