Project overview
OmniVoice Studio combines voice cloning, voice design, video dubbing, and system-wide dictation in a desktop app that runs on your own machine without an account or API key. It can create a voice from a short sample and take a video through transcription, translation, re-voicing, and export. The project is still in active beta, and its local backend does not support Intel Macs.
Repository facts
- Primary language
- Python
- License
- Custom / other
- Repository updated
- Jul 14, 2026
- Default branch
- main
Resource types
Desktop app
Use cases
Media, audio and videoVideo creation and editing
Operating systems
LinuxmacOSWindows
Runtime
DesktopLocal
Capabilities
Audio processingTranscriptionTranslationVideo processing