What it is
A desktop app that clones voices from short audio samples, generates speech in 23 languages using eight swappable TTS engines, and adds system-wide dictation with a global hotkey using Whisper. It includes a multi-track timeline for podcasts and narratives, audio effects, a REST API, and an MCP server so coding agents can speak in a chosen voice. Creators and developers who want voice work to stay on their own machine run it locally on macOS, Windows, Linux, or Docker.