Skip to content
RepoQuarry

VoiceStudio debpalash/VoiceStudio

Local desktop app for voice cloning, voice design, video dubbing, dictation, transcription and audiobooks, built on OmniVoice and other engines.

Creator kit + Compare GitHub ↗ Install guide (official) ↗

VoiceStudio at a glance

Checked 15 Oct 2026

VoiceStudio is an Electron desktop app (Windows, macOS Apple Silicon, Linux, Docker) with a Python backend that clones and designs voices, dubs video, transcribes and builds audiobooks on your own hardware; CPU works, slower. App code is AGPL-3.0, but the default engine's OmniVoice weights are CC-BY-NC, so commercial use of the default setup is not allowed. Other engines carry their own terms. A paid Pro tier and commercial licence exist.

Cite this pageRepoQuarry. “VoiceStudio.” Checked 15 Oct 2026. https://repoquarry.dev/projects/voicestudio

How much of ElevenLabs does it replace?

3 of 4 jobs. Covers speech generation, cloning, transcription and dubbing locally; no voice agents. Default OmniVoice weights are non-commercial.

Partial: Speech generation Partial replacement
Partial: Voice cloning Partial replacement
Partial: Speech recognition Partial replacement
No: Voice agents Not covered

For voice agents, see other ElevenLabs alternatives. You may also need to build an interface, an API server and hosting yourself.

Facts, with sources

Every answer links to where we found it. We read the documentation; we did not install it.

Report a correction
QuestionAnswerSourceChecked
Runs on my machine? Confirmed: Yes, desktop app and backend run on your hardware; remote services optional Local workflows run on your hardware. Remote services are optional; usage analytics requires consent. github.com · VoiceStudio#readme ↗ 1d ago
Code licence Partial: AGPL-3.0-only (copyleft, network clause); paid commercial licence offered for closed-source use That includes commercial and internal business use of the application itself. github.com · LICENSE-NOTICE.md ↗ 1d ago
Model weights licence No: Default OmniVoice weights CC-BY-NC (non-commercial); other engines have their own terms The pre-trained model is licensed under the CC-BY-NC due to constraints from its training data (e.g., Emilia). huggingface.co · OmniVoice ↗ 1d ago
Commercial use No: No with the default OmniVoice model (non-commercial weights); app code alone allows it under AGPL The default `k2-fsa/OmniVoice` model card identifies its code as Apache-2.0 and pretrained weights as CC-BY-NC. github.com · LICENSE-NOTICE.md ↗ 1d ago
Paid services needed? Partial: None required; VoiceStudio Pro features and a closed-source commercial licence are paid extras Commercial use under the AGPL-3.0 is free. github.com · LICENSE-NOTICE.md ↗ 1d ago
Hardware Confirmed: NVIDIA CUDA or Apple Silicon MPS accelerated; CPU-only works but slower (~5 GB disk); Intel Mac UI only Fully usable on the CPU, slower; setup installs the small CPU build of PyTorch (about 5 GB free disk) github.com · VoiceStudio#get-started ↗ 1d ago
Operating systems Confirmed: Windows (.exe), macOS Apple Silicon (.dmg), Linux (.AppImage/.deb), Docker; Intel Mac needs a remote backend Intel Mac | App UI only; connect to a remote backend github.com · VoiceStudio#get-started ↗ 1d ago
Setup effort Confirmed: Easy; installer from Releases or one-command install script; models download on first use On Windows, run `irm https://voicestudio.sh/install | iex` in PowerShell. github.com · VoiceStudio#one-command-install-macos--linux ↗ 1d ago

Get the weekly top 5 and what’s new, every Monday

We’ll email you once a week. Unsubscribe any time. We never share your email.

Cookie preferences

Choose what we may store in your browser. You can change this any time from Cookie settings in the footer.

Essential

Security, and remembering this choice. rq-consent · 12 months

Always on