v0.5.8 · 2026-11-12downloads on GitHub: ~596,000
Download VoiceStudio
VoiceStudio Pro
Everything in the free app, plus the tools for paid work.
- Batch dubbing
- Watch folders
- Remote GPU workers
- Commercial licence
Desktop
Stable v0.5.8Beta v0.5.9-beta.2
macOS (Apple Silicon)
M1 · M2 · M3 · M4 · 285 MB
macOS (Intel)
Intel x64 · remote backend required · 291 MB
Windows (x64)
Installer · 233 MB
Linux (x64)
Portable AppImage · 289 MB
Phones
Android
APK · Android 10 or newer · 137 MB
iOS
Unsigned IPA · sign it yourself · 25 MB
F-Droid
More ways to install
Snap
Linux on Snap Store
Install from the terminal
Requires snapd. Prefer AppImage? Download above
Arch Linux
AUR · voicestudio-bin
Docker
palashdeb/omnivoice-studio
Docker guide
Headless web studio for a GPU box, homelab, or anywhere Docker runs.
docker run -d --pull always --name omnivoice \ -p 127.0.0.1:3900:3900 \ -v omnivoice-data:/app/omnivoice_data \ -v ~/.cache/huggingface:/root/.cache/huggingface \ palashdeb/omnivoice-studio:latest
Open
http://localhost:3900once it starts. First run pulls model weights. Docker guide
What's newv0.5.8
FAQ
- Does it need an account or API key?
- No. VoiceStudio runs entirely on your machine. Clone, dub, and dictate without signing in or talking to a cloud API.
- Desktop vs Docker — which should I use?
- Desktop is the full app with auto-updates. Docker is the headless web UI (port 3900) for servers, homelabs and GPU boxes. Both run the same engines.
- How much hardware do I need?
- About 8 GB RAM (16 GB+ recommended) and ~10 GB disk for models. GPU optional — 4 GB VRAM works with CPU offload; no GPU is fine, just slower.
- Where are older versions?
- Every release and asset lives on GitHub Releases. Docker has :latest for the newest build and :rocm for AMD.
- What is Beta?
- Betas are test builds of the next release, published on GitHub before it ships. They get new features first and may be unstable. Use stable for day-to-day work; switch channels in Settings → About.