Open Source AI Voice Studio
Explore VoiceStudio, a local open-source AI voice studio for voice cloning, text to speech, video dubbing, transcription and voice design. Find guides and downloads for Windows, macOS and Linux.
Available for Windows, macOS & Linux · v0.5.6
docker pull palashdeb/omnivoice-studioExplore all features
Voice cloning
Create a reusable voice from a short recording, then turn your scripts into familiar, natural speech.
Explore workflowText to speech
Transform scripts, articles, and ideas into expressive audio with local text-to-speech models.
Explore workflowVideo dubbing
Translate and dub video while keeping the rhythm and personality of the original.
Explore workflowLess typing. More creating.
Turn recordings into searchable text for interviews, meetings, and your next big idea.
Explore workflowImagine a new voice
Describe the character, tone, and style you want. Build a voice that fits the story.
Explore workflowBuilt for your workflow
Manage models and projects in one place, or connect your tools through the local audio API.
Explore workflowCREATIVE FREEDOM, INCLUDED.
Your creativity shouldn’t
come with a meter.
Your audio stays on your machine. Your tools stay in your hands. Download the models you need and create locally, without a cloud account or per-character billing.
- Private by design
- Create at your own pace
- Open source, from the start
Made on your machine.
Not on someone else’s server.
VOICE STUDIO 100% LOCALMADE FOR YOUR NEXT GREAT THING.
What will you create?
One tool. A whole world of stories.
Content that travels
Give your videos a voice and bring them to new audiences with multilingual dubbing.
Stories worth listening to
Turn chapters, characters, and long-form writing into audiobooks and audio stories.
Learning without borders
Make course narration and language resources for learners around the world.
Tools that work together
Build audio into your own applications with a local, OpenAI-compatible API.
FROM IDEA TO AUDIO.
Three steps. Your next creation.
Make yourself at home
Download the app for your operating system. No account required.
Find your voice
Install a compatible model and choose a voice, or add your own recording.
Create something great
Write, generate, and export your audio. Keep creating on your terms.
Is VoiceStudio really free?+
The open-source desktop application is available under AGPL-3.0. Upstream also offers separate paid commercial builds. Review the software and model licenses for your use.
Does my audio leave my computer?+
Local generation processes your audio on your machine. Internet access is needed to download models and updates. Third-party services you choose to connect have their own policies.
Do I need a powerful GPU?+
You can start with around 8 GB of RAM. A supported GPU can speed up generation. Memory, storage, and hardware requirements vary by model.
Which languages are supported?+
The upstream project advertises up to 646 languages across its engines. Language coverage, quality, and features depend on the model you install.
Can I use it for commercial projects?+
Check both the application license and each model’s license before commercial use. Open source does not mean every model has identical commercial terms.
Your next story starts here.
Find your voice. Make it heard.
Download freeFree to download. Yours to explore.