Voicebox

Voicebox is an open-source, local AI voice studio designed for voice cloning, speech generation, transcription, and voice personalized agent interaction. It runs entirely on the user’s machine, supporting macOS, Windows, and Linux, and does not require API keys or internet access. With multiple built-in TTS and ASR models, it allows users to create, customize, and control voices for apps, games, dictation, and accessibility—making it a professional alternative to cloud-based providers for developers, creators, and anyone seeking high privacy, cost efficiency, and creative control.