Reading the repo
Reading the repo
Assembly instructions
VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.
Fresh setup, read just now
The maintainers included scripts/install.sh. Run it from the cloned folder after reading it.
bash scripts/install.sh
Also: scripts/install.ps1
Will it work on my device?
Choose your system, then expand an installation method.
<a id="install-macos"></a>
<details> <summary><img src="docs/assets/platforms/apple.svg" alt="" width="20" height="20" /> <strong>macOS</strong> · Homebrew · DMG · installer</summary> <blockquote>Stable · Apple Silicon<br />macOS 13.3+ · Apple Silicon: local engines with Metal (MPS).
<a href="https://github.com/debpalash/homebrew-tap"><img src="https://img.shields.io/badge/Homebrew-27272a?style=flat-square&logo=homebrew&logoColor=ffffff" alt="Homebrew" height="20" /></a>
brew tap debpalash/tap
brew trust --cask debpalash/tap/voicestudio
brew install --cask debpalash/tap/voicestudio
Download the DMG for your Mac, open it and drag VoiceStudio into Applications.
</details> <details> <summary>One-command installer</summary>curl -fsSL https://voicestudio.sh/install | sh
The app UI runs on Intel; connect it to a VoiceStudio backend on another computer.
</details></blockquote> </details>[!NOTE] On macOS, "VoiceStudio is damaged and can't be opened" means Gatekeeper blocked the app, not that the download is broken. See the Gatekeeper fix.
<a id="install-windows"></a>
<details> <summary><img src="docs/assets/platforms/windows.svg" alt="" width="20" height="20" /> <strong>Windows</strong> · PowerShell · EXE</summary> <blockquote>Stable · x64<br />Windows 10/11 x64 · NVIDIA CUDA · AMD ROCm (opt-in) · CPU.
irm https://voicestudio.sh/install.ps1 | iex
Download the Windows installer · Guide · AMD ROCm
<details> <summary>Windows on ARM · experimental</summary>Native app UI; the x64 Python backend runs under emulation on the CPU.
</details> </blockquote> </details><a id="install-linux"></a>
<details open> <summary><img src="docs/assets/platforms/linux.svg" alt="" width="20" height="20" /> <strong>Linux</strong> · AUR · Snap · DEB · AppImage · Nix</summary> <blockquote>Stable · x64<br />Linux x64 · NVIDIA CUDA · CPU · Vulkan for supported GGUF engines.
<details> <summary>One-command installer</summary>curl -fsSL https://voicestudio.sh/install | sh
<a href="https://aur.archlinux.org/packages/voicestudio-bin"><img src="https://img.shields.io/badge/AUR-1793d1?style=flat-square&logo=archlinux&logoColor=ffffff" alt="AUR" height="20" /></a>
yay -S voicestudio-bin
Also available through paru -S voicestudio-bin.
Development sources · yay -S voicestudio-git
sudo pacman -S --needed base-devel git
git clone https://aur.archlinux.org/voicestudio-bin.git
cd voicestudio-bin
makepkg -s
sudo pacman -U ./voicestudio-bin-*.pkg.tar.zst
Download the .deb into the current folder, then install it:
sudo apt install ./VoiceStudio-*-linux-x64.deb
<a href="https://snapcraft.io/voicestudio"><img src="https://img.shields.io/badge/Snap%20Store-27272a?style=flat-square&logo=snapcraft&logoColor=ffffff" alt="Snap Store" height="20" /></a>
With snapd installed:
sudo snap install voicestudio
To enable microphone access:
sudo snap connect voicestudio:audio-record
Download the AppImage into the current folder, then launch it:
chmod +x VoiceStudio-*-linux-x64.AppImage
./VoiceStudio-*-linux-x64.AppImage
Enter the repository’s FHS development environment, then run from source:
git clone https://github.com/debpalash/VoiceStudio.git
cd VoiceStudio
nix develop .#fhs
bun run dev
<a id="install-docker"></a>
<details> <summary><img src="docs/assets/platforms/docker.svg" alt="" width="20" height="20" /> <strong>Docker</strong> · GHCR · Docker Hub</summary> <blockquote>Stable images · CPU ·
…
This app runs on the device, not on your macOS computer. Download it, then install it from the computer with adb (turn on ADB debugging in the device's Developer Options first).
adb connect <device-ip>:5555 adb install -r "VoiceStudio-0.5.7-android.apk"
curl -LO "https://github.com/debpalash/VoiceStudio/releases/download/v0.5.7/VoiceStudio-0.5.7-mac-arm64.dmg" open "VoiceStudio-0.5.7-mac-arm64.dmg"
curl -LO "https://github.com/debpalash/VoiceStudio/releases/download/v0.5.7/VoiceStudio-0.5.7-mac-arm64.zip" unzip "VoiceStudio-0.5.7-mac-arm64.zip"
curl -LO "https://github.com/debpalash/VoiceStudio/releases/download/v0.5.7/VoiceStudio-0.5.7-mac-x64.dmg" open "VoiceStudio-0.5.7-mac-x64.dmg"
curl -LO "https://github.com/debpalash/VoiceStudio/releases/download/v0.5.7/VoiceStudio-0.5.7-mac-x64.zip" unzip "VoiceStudio-0.5.7-mac-x64.zip"
brew install --cask debpalash/tap/voicestudio
curl -fsSL https://voicestudio.sh/install | sh
curl -fsSL https://voicestudio.sh/install | sh -s -- --version X.Y.Z # a specific release
curl -fsSL https://voicestudio.sh/install | sh -s -- --main # build current main
curl -fsSL https://voicestudio.sh/install | sh -s -- --uninstall # remove the app, keep your data
From the README, exactly as the maintainers wrote it.
A self-hosted app: Docker runs it on your computer and you open it in the browser. Needs Docker Desktop (or Docker Engine on Linux). Run docker compose commands inside the cloned repo folder.
docker run -d --name omnivoice -p 127.0.0.1:3900:3900 -e OMNIVOICE_API_KEY -e OMNIVOICE_DATA_DIR=/app/omnivoice_data -v omnivoice-data:/app/omnivoice_data ghcr.io/debpalash/voicestudio:stable
From the README, exactly as the maintainers wrote it.
No reports for macOS yet.
Opens a chat with this manual already filled in, for macOS. It uses your own account; gitmanual sends nothing.