debpalash/VoiceStudio

VoiceStudio

Open-source voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

Website · Download · Get started · Docs · Discord · 简体中文

Your voice. Your workflow.

| Create | Produce | Connect | | :--- | :--- | :--- | | Clone a voice or design your own | Dub videos with timed speech | Local API & MCP for agents | | Dictate with a floating widget | Stories, audiobooks & batch jobs | Optional remote workers |

Start with VoiceStudio (default, powered by k2-fsa/OmniVoice), or choose another engine. Features & engine catalog.

Local workflows run on your hardware. Remote services are optional; usage analytics requires consent.

Explore the workspaces · Clone, dub, design & models

Voice cloning	Video dubbing
Voice design	Local models

Get started

Download from Releases, then follow your platform guide:

macOS · Windows · Linux · Docker

Open Voice cloning, choose a voice or add a clean reference recording, enter your text, and generate. Install the required model when prompted. Hardware needs vary by engine; see performance.

Install with prompt

Copy this prompt into your coding agent to install VoiceStudio and configure it for your device:

Install and configure the VoiceStudio Electron desktop app on this device,
then verify it works. Tauri is archived; do not install or launch it.
Repository: https://github.com/debpalash/VoiceStudio
Read the repository's install guide for my OS, docs/performance.md, and
skills/voicestudio/SKILL.md. Install the voicestudio audio-workflow skill
with npx skills add debpalash/VoiceStudio if your agent supports skills;
otherwise follow that SKILL.md directly.
Detect my OS, CPU architecture, GPU, available RAM/VRAM, free disk space,
and any existing VoiceStudio installation, backend, or downloaded models.
Reuse existing data and models. Prefer the latest stable Electron installer
for my OS and architecture; select an asset named VoiceStudio-Electron.
For source setup, follow electron/README.md: bun install, then bun run dev
from the repository root. Let Electron supervise the backend; do not start
a second backend or use legacy tauri scripts.
If migrating from Tauri, follow docs/electron-migration.md and back up first.
Configure local voice cloning using a supported engine and acceleration
that fit this device. Keep working defaults and verify the actual execution
device rather than assuming GPU support. Install required dependencies;
reuse a suitable installed model, or explain the download size and license
and ask before downloading one. Keep cloud services and analytics opt-in.
Start the app, check /health at the configured backend address (default
http://localhost:3900), and discover its API through /openapi.json. Generate
a short test with a bundled or authorized voice and verify the audio file.
Report the installed version, engine, actual device, data location, audio
output path, and how to reopen the app. Complete the setup, not just a plan;
identify any permissions or manual steps you cannot perform.

git clone https://github.com/debpalash/VoiceStudio.git
cd VoiceStudio
bun install
bun run dev

Electron is the only maintained desktop app. Version 0.5.3 was the final Tauri release. Existing Tauri users must install Electron separately. Root development, build, test, and release commands target Electron; Tauri source is archived and receives no further updates.

Documentation

| Need | Start here | |---|---| | Setup help | Troubleshooting · Model downloads | | Models & audio quality | Engine guides · Benchmarks | | Integrations | Local API · MCP · Examples | | Development | Contributing · Electron · Changelog |

Agent skills: npx skills add debpalash/VoiceStudio — choose voicestudio for audio workflows or voicestudio-maintainer for repository maintenance.

Sponsors

Become a featured partner. Apply for a paid placement · Email us

Support development: Ko-fi · PayPal · Sponsorship details

License & responsible use

AGPL-3.0. Models have their own licenses; review them before commercial use. Clone voices only with permission. See license details.