Local-first open-source voice cloning, dubbing, and audiobook studio.
Clone voices, dub videos, and design audio locally with 646 language support.
VoiceStudio is a desktop application designed for local voice cloning, video dubbing, and transcription. It suits audio producers and developers wanting to run speech models directly on their own hardware.
The application provides workspaces for voice cloning, voice design, video dubbing with timed speech, dictation, and audiobook creation. It defaults to the OmniVoice engine while supporting multiple alternative models and local API integrations.
It suits professionals and creators needing private, local control over voice synthesis and video dubbing workflows. It does not suit users looking for a simple web service without hardware setup requirements.
Clone voices and design custom audio profiles directly on your hardware.
Dub videos with synchronized timed speech across supported languages.
Integrate with local APIs and Model Context Protocol for agent workflows.
Use a floating widget for speech-to-text dictation and transcription.
Free under the AGPL-3.0 licence. The repository mentions no paid hosted option, so your only cost is running it yourself on local hardware.
873 open remote AI-training roles, updated November 15, 2026; most pay $20–$170 an hour. Zekai lists them free; the application goes to the employer’s platform.
These reviewed AI tools do the same job instantly — from our scored directory.
VoiceStudio supports macOS, Windows, and Linux via its Electron desktop application and Docker.
Yes, workflows run locally on your hardware, and remote services or analytics are entirely optional.
See Zekai first in Google