VoiceStudio
AI voice studio. On your device.
Clone, design, dub, dictate, transcribe and narrate in 646 languages.
Runs on your laptop, desktop, servers, phone, tablets and more
Website · Download · Get started · Docs · VoiceStudio Pro · VoiceStudio Cloud
🇬🇧 English · 🇨🇳 简体中文 · 🇯🇵 日本語 · 🇰🇷 한국어 · 🇷🇺 Русский · 🇸🇦 العربية · 🇩🇪 Deutsch · 🇪🇸 Español · 🇫🇷 Français · 🇮🇳 हिन्दी
🇮🇩 Bahasa Indonesia · 🇮🇹 Italiano · 🇳🇱 Nederlands · 🇵🇱 Polski · 🇵🇹 Português · 🇹🇭 ไทย · 🇹🇷 Türkçe · 🇹🇼 繁體中文 · 🇺🇦 Українська · 🇻🇳 Tiếng Việt
Strategic sponsors 
Demo workspace · Default dark theme · Watch the HD tour
What you can do
 Voice cloning Turn a clean reference recording into speech in a familiar voice. |
 Video dubbing Translate and dub videos with speech timed to the original. |
 Voice design Describe a voice in words and generate it. |
 Local models Choose your engines and download only the models you need. |
More screenshots
 Workspace overview |
 Model packs |
- Dictate & transcribe — A floating dictation widget and local transcription
- Narrate & batch — Stories, audiobooks and queued jobs
- Connect & automate — Local API, MCP, reusable recipes and watch folders
Pro and Cloud
Everything above is free, runs on your own hardware and needs no account. Pro and Cloud are optional.
 VoiceStudio ProFor paid client work across more than one machine.
See Pro plans → |
 VoiceStudio CloudA hosted voice and dubbing API, coming soon. No GPU needed.
Join Cloud early access → |
Platforms
Experimental Windows ROCm setup supports selected RDNA 2 RX 6000 GPUs with targets gfx1030, gfx1031 or gfx1032; RX 6500 XT (gfx1034) is excluded. GPU transcription uses a CTranslate2 build with native
gfx1031 kernels that this repository builds from upstream source and pins by
hash, and setup checks actual GPU kernel execution. RX 6700 XT tests also cover native Torch speech generation and
PyTorch Whisper. ROCm 10 faster-whisper uses a separate inference process to
preserve safe CPU selection and fallback. Other cards and workloads retain the qualification limits in the guide.
Performance presets validate changed engine selections in an offline child
process before saving them, preserving fallback when an installed runtime fails.
Choose your system, then expand an installation method.
Native GGUF engines additionally support engine-specific Vulkan acceleration on AMD, Intel and NVIDIA GPUs (OmniVoice, CosyVoice). OmniVoice GGUF selects its GPU and model size automatically on Windows and Linux. Vulkan discovery retries a stalled hidden probe with a native summary; Windows and Linux desktop builds fail rather than silently ship without their Vulkan module.
macOS · Homebrew · DMG · installer
Stable · Apple Silicon
macOS 13.3+ · Apple Silicon: local engines with Metal (MPS).
brew tap debpalash/tap brew trust --cask debpalash/tap/voicestudio brew install --cask debpalash/tap/voicestudio
DMG
Download the DMG for your Mac, open it and drag VoiceStudio into Applications.
One-command installer
curl -fsSL https://voicestudio.sh/install | sh
Intel Mac · remote backend · Limited
The app UI runs on Intel; connect it to a VoiceStudio backend on another computer.
[!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.
Windows · PowerShell · EXE
Stable · x64
Windows 10/11 x64 · NVIDIA CUDA · AMD ROCm (opt-in) · CPU.irm https://voicestudio.sh/install.ps1 | iexDownload the Windows installer · Guide · AMD ROCm
Windows on ARM · experimental
Native app UI; the x64 Python backend runs under emulation on the CPU.
Linux · AUR · Snap · DEB · AppImage · Nix
Stable · x64
Linux x64 · NVIDIA CUDA · CPU · Vulkan for supported GGUF engines.
One-command installer
curl -fsSL https://voicestudio.sh/install | sh
Arch / Manjaro / EndeavourOS · AUR
yay -S voicestudio-binAlso available through
paru -S voicestudio-bin.Development sources ·
yay -S voicestudio-git
Build from AUR and install with pacman
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
Ubuntu / Debian / Linux Mint · DEB
Download the
.debinto the current folder, then install it:sudo apt install ./VoiceStudio-*-linux-x64.deb
Snap · Ubuntu, Fedora, openSUSE and more
With snapd installed:
sudo snap install voicestudioTo enable microphone access:
sudo snap connect voicestudio:audio-record
Any Linux distribution · AppImage
Download the AppImage into the current folder, then launch it:
chmod +x VoiceStudio-*-linux-x64.AppImage ./VoiceStudio-*-linux-x64.AppImage
Nix / NixOS · source environment
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
Docker · GHCR · Docker Hub
Stable images · CPU · NVIDIA CUDA · AMD ROCm.
Run locally on the CPU (Bash)
export OMNIVOICE_API_KEY="$(openssl rand -hex 32)" docker run -d --name omnivoice \ -p 127.0.0.1:3900:3900 \ -e OMNIVOICE_API_KEY \ -e OMNIVOICE_DATA_DIR=/app/omnivoice_data \ -v omnivoice-data:/app/omnivoice_data \ ghcr.io/debpalash/voicestudio:stable printf 'API key: %s\n' "$OMNIVOICE_API_KEY"Open http://localhost:3900 and use the API key printed below.
NVIDIA, AMD ROCm and Compose instructions
Docker Hub mirror:
palashdeb/omnivoice-studio:stable
Android · APK · Obtainium · F-Droid repository
Android 10+ · Preview · On-device, offline after model download.
F-Droid · VoiceStudio repository
Add this repository in an F-Droid-compatible client; verify the fingerprint in the guide.
https://debpalash.github.io/VoiceStudio/fdroid/repo
Obtainium · GitHub releases
Add this source in Obtainium, or import the provided configuration.
https://github.com/debpalash/VoiceStudio
Install over USB with adb
adb install -r VoiceStudio-*-android.apk
iPhone / iPad · IPA · sideloading
iOS / iPadOS 17+ · Preview · On-device, offline after model download.
Download the IPA and follow the signing and sideloading instructions.
Desktop and phone installers are on the latest release; Docker images come from GHCR. No GPU? The app is fully usable on the CPU, just slower. Native GGUF engines can also use Vulkan on AMD, Intel and NVIDIA GPUs; OmniVoice GGUF picks its GPU and model size automatically on Windows and Linux (OmniVoice, CosyVoice). Speed by engine and hardware: performance.
Get started
Install using the options above. Then open Voice cloning, pick a voice or add a clean reference recording, type your text and generate. The app asks before it downloads any model.
More install options: a specific version, current main, uninstall, from source, with a coding agent
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 dataIf voicestudio.sh is unreachable, run the script straight from the repository:
curl -fsSL https://raw.githubusercontent.com/debpalash/VoiceStudio/main/scripts/install.sh | sh.
Prerequisites and behavior: installer guide.
From source
git clone https://github.com/debpalash/VoiceStudio.git
cd VoiceStudio
bun run devbun run dev installs the JavaScript dependencies and, when using a supported
local backend, the Python dependencies before launching Electron. Run
bun run setup:api directly when you only need to rebuild the Python environment.
See Electron setup.
With a coding agent (Claude Code, Codex, Cursor, …), paste:
Install the VoiceStudio app on this device and verify it works, following
https://github.com/debpalash/VoiceStudio/blob/main/docs/install/agent.mdUpgrading from 0.5.3 or older (the Tauri app)? Install the new app separately.
Documentation
| Need | Start here | |---|---| | Setup help | Troubleshooting · Model downloads | | Guides | Multi-speaker dubbing · Expressive speech · Exporting dubs | | Models & quality | Engine guides · whisper.cpp ASR · Benchmarks | | Integrations | CLI · Local API · MCP · Examples | | Phone apps | iOS and Android | | Development | Contributing (sign the CLA before your first PR) · Changelog |
Agent skills: npx skills add debpalash/VoiceStudio (voicestudio for audio work, voicestudio-maintainer for the repo).
Sponsors
The VoiceStudio app is free and needs no paid cloud. Sponsors keep it shipping: they fund maintainer time, test hardware, code-signing and release infrastructure.
For sponsorship inquiries, contact [email protected].
Other projects
More open-source tools from the people building VoiceStudio.
- OpenGTM — Find and enrich companies and people in a self-hosted go-to-market workspace. Source.
- Opal — Watch, stream and browse your media in one native, open-source player. Source.
- Supermetry — Understand your websites and products with self-hosted, cookie-free analytics. Source.
Team
Core team
 Palash Debnath Creator and Core Team palash.dev · GitHub · X |
 Shimul Debnath Core Team shimul.me · GitHub · X |
Contributors
Thank you to everyone who sends code, reports, translations and ideas. All contributors · Contribute
License & responsible use
AGPL-3.0 covers the app, including commercial use under its terms. Model weights, voices and generated output have their own licences, which the Model Manager shows for each model (inventory). Clone a voice only with its owner's permission. Details: LICENSE-NOTICE.md.
Community tutorials
Nafay 3D · Samuel Gregory · kilObit
Disclaimer
VoiceStudio users are strictly prohibited from using it for unauthorized voice cloning, voice impersonation, fraud, scams, or any other illegal or unethical activities. All users shall ensure full compliance with applicable local laws, regulations, and ethical standards. The developers assume no liability for any misuse of VoiceStudio and advocate for responsible AI development and use, encouraging the community to uphold safety and ethical principles in AI research and applications.