VoiceStudio
Local desktop studio for voice cloning, dubbing, and transcription
What it is
A desktop app that runs speech models on your own hardware to clone voices, design new ones from a text description, dub videos with timed speech, transcribe audio, and produce audiobooks across hundreds of languages. It includes a floating dictation widget, batch jobs, watch folders, and a local API and MCP server so agents can call it. Creators and podcasters use it to produce narration and translated voiceovers without sending audio to a cloud service, with GPU acceleration on CUDA and Apple Silicon or slower CPU-only use.