voicestudio is an open-source local voice workflow application for voice cloning, voice design, video dubbing, dictation, transcription, and audiobook production. It supports local workflows while remote services are optional.
Project overview
voicestudio brings multiple voice production workflows into a desktop application, including voice cloning, timed video dubbing, dictation, transcription, stories, audiobooks, and batch jobs.
Users seeking a desktop application for local voice generation, dubbing, dictation, transcription, or audiobook workflows.
Users who need voice cloning with a selected voice or a clean reference recording.
Key capabilities
Creates speech using a selected voice or a clean reference recording.
Supports designing a voice for speech workflows.
Dubs videos with timed speech.
Provides dictation through a floating widget.
Supports transcription workflows.
Supports stories, audiobooks, and batch jobs.
Limitations and risks
Hardware needs vary by engine, so deployment planning should account for the selected engine's requirements.
Models have their own licenses, which should be reviewed before commercial use.
Use voice cloning only with permission.
Using models commercially without reviewing their individual licenses presents a documented licensing risk; review the applicable model licenses before commercial use.
Getting started
Download voicestudio from Releases, follow the guide for macOS, Windows, or Linux, open Voice cloning, choose a voice or add a clean reference recording, enter text and generate, then install the required model when prompted. The default workflow is powered by k2-fsa/OmniVoice.
Evidence and sources
GitHub project description: VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
README: | Clone a voice or design your own | Dub videos with timed speech | Local API & MCP for agents |
README: Open **Voice cloning**, choose a voice or add a clean reference recording, enter your text, and generate. Install the required model when prompted. Hardware needs vary by engine;…
README: Local workflows run on your hardware. Remote services are optional; usage analytics requires consent.
README: > **Electron is the primary desktop app.**