TTSbox

TTSbox is a local-first AI voice workstation for text-to-speech, voice cloning, recording, transcription, and multi-character audio production. It keeps voice samples, models, and generated audio on the user’s machine instead of relying on third-party SaaS, making it useful for creators, podcasters, storytellers, and developers who need private, reusable voice workflows. TTSbox is built for practical production, from collecting voice samples to editing scenes, mixing roles, and exporting finished audio.