debpalash/VoiceStudio

站内导读

中文 VoiceStudio 是开源桌面语音工具，覆盖声音克隆、声音设计、视频配音、听写、转写与有声书制作，支持 646 种语言。本地流程在自有硬件上运行，远程服务可选。内置 OmniVoice 引擎，也可换用其他引擎，并提供本地 API 与 MCP 供 Agent 调用。适合需要离线处理语音、注重数据留存的内容创作者与开发者。

README · 详细文档

来源 · 查看原文

<div align="center"> <img src="docs/logo.png" alt="VoiceStudio" width="88" /> <h1>VoiceStudio</h1> <p> <a href="https://trendshift.io/repositories/28176?utmsource=repository-badge&utmmedium=badge&utmcampaign=badge-repository-28176" target="blank" rel="noopener noreferrer"><img src="https://trendshift.io/api/badge/repositories/28176" alt="VoiceStudio ranking on Trendshift" width="220" height="48" /></a> </p> <p><strong>Open-source voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.</strong></p> <p> <a href="https://voicestudio.sh/?utmsource=github&utmmedium=readme&utmcampaign=project">Website</a> · <a href="https://github.com/debpalash/VoiceStudio/releases/latest">Download</a> · <a href="#get-started">Get started</a> · <a href="#documentation">Docs</a> · <a href="https://discord.gg/bzQavDfVV9">Discord</a> · <a href="docs/readme/READMECN.md">简体中文</a> · <a href="docs/readme/README_JA.md">日本語</a> </p> <p> <a href="https://github.com/debpalash/VoiceStudio/actions/workflows/ci.yml"><img src="https://img.shields.io/github/actions/workflow/status/debpalash/VoiceStudio/ci.yml?branch=main" alt="CI" /></a> <a href="https://github.com/debpalash/VoiceStudio/releases/latest"><img src="https://img.shields.io/github/v/release/debpalash/VoiceStudio" alt="Latest release" /></a> <a href="LICENSE"><img src="https://img.shields.io/badge/license-AGPL--3.0-blue" alt="AGPL-3.0" /></a> <a href="https://supermetry.com"><img src="https://app.supermetry.com/px/zfjiv7psp4ed.svg?c=VoiceStudio&style=stats" alt="views" /></a> </p> </div>

A tour of the Electron app: voice cloning, voice design, dubbing, and model management

Your voice. Your workflow.

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.

<details> <summary><strong>Explore the workspaces</strong> · Clone, dub, design & models</summary>

<table> <tr> <td><img src="docs/media/electron/voice-cloning.png" alt="Electron voice cloning workspace with the bundled demo voice" width="100%" /></td> <td><img src="docs/media/electron/dubbing.png" alt="Electron video dubbing workspace" width="100%" /></td> </tr> <tr><td align="center">Voice cloning</td><td align="center">Video dubbing</td></tr> <tr> <td><img src="docs/media/electron/voice-design.png" alt="Describe a voice in the Electron voice design workspace" width="100%" /></td> <td><img src="docs/media/electron/models.png" alt="Install and manage local speech models" width="100%" /></td> </tr> <tr><td align="center">Voice design</td><td align="center">Local models</td></tr> </table>

</details>

OmniVoice GGUF source builds can optionally use Vulkan on Windows and Linux; see the native engine guide for build requirements, CPU fallback, and device overrides.

Get started

One-command install (macOS / Linux)

# Latest Electron release
curl -fsSL https://voicestudio.sh/install | sh

# A specific published Electron release (replace X.Y.Z)
curl -fsSL https://voicestudio.sh/install | sh -s -- --version X.Y.Z

# Build current main and install the desktop app
curl -fsSL https://voicestudio.sh/install | sh -s -- --main

# Uninstall the app, keeping your data
curl -fsSL https://voicestudio.sh/install | sh -s -- --uninstall

On Windows, run irm https://voicestudio.sh/install | iex in PowerShell.

If voicestudio.sh/install is unreachable or returns 404, run the same script straight from the repository, or clone it and run scripts/install.sh:

curl -fsSL https://raw.githubusercontent.com/debpalash/VoiceStudio/main/scripts/install.sh | sh

Release downloads require curl and a SHA-256 tool. --main requires Git, Node.js 22+, Bun, Rust/Cargo, and platform build tools; see installer prerequisites and behavior. The installer preserves your settings, projects, and models. Older versions must contain Electron packages; it never falls back to archived Tauri builds.

Or download from Releases (macOS .dmg, Windows .exe, Linux .AppImage or .deb) and follow your platform guide:

macOS · Windows · Linux · Docker

| Hardware | Support | |---|---| | NVIDIA GPU (Windows / Linux) | CUDA acceleration | | AMD Radeon / supported Ryzen AI (Windows) | CPU by default; opt-in Windows ROCm setup for AMD's Windows 11 hardware matrix. Setup distinguishes package repair from host failures; install the VC++ runtime manually first. Optional engines have separate limits; Vulkan engines retain their own runtime. | | Apple Silicon | Metal (MPS) acceleration | | AMD GPU | Opt-in native CosyVoice GGUF can use Vulkan when the community runtime is built with Vulkan; verified on RX 6700 XT (setup) | | No dedicated GPU (Intel/AMD integrated graphics, older PCs) | Fully usable on the CPU, slower; setup installs the small CPU build of PyTorch (about 5 GB free disk) | | Windows on ARM (Snapdragon X etc.) | Experimental, validation pending: native ARM64 app, x64 Python backend under emulation, CPU only | | Intel Mac | App UI only; connect to a remote backend (why) |

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

Paste into your coding agent (Claude Code, Codex, Cursor, …):

Install the VoiceStudio Electron app on this device and verify it works, following
https://github.com/debpalash/VoiceStudio/blob/main/docs/install/agent.md

The agent guide covers hardware detection, reusing existing data, asking before model downloads, and a test generation. Agents that support skills can also run npx skills add debpalash/VoiceStudio.

<details> <summary><strong>Run the Electron preview from source</strong></summary>

git clone https://github.com/debpalash/VoiceStudio.git
cd VoiceStudio
bun install
bun run setup:api  # prepare Python dependencies before starting Electron
bun run dev

See Electron setup for prerequisites and backend configuration.

Use bun run smoke-test to build and launch an isolated packaged Electron app. Add -- --install for the networked managed-runtime installation check.

</details>

Electron is the only desktop app and web UI. Version 0.5.3 was the final Tauri release. Existing Tauri users must install Electron separately. The retired Tauri shell and legacy UI entry points have been removed.

Documentation

| Need | Start here | |---|---| | Setup help | Troubleshooting · Model downloads | | Models & audio quality | Engine guides · whisper.cpp ASR · Benchmarks | | Integrations | Local API · MCP · Examples | | Phone apps (preview, run offline) | iOS and Android | | Development | Contributing (CLA signing guidance for your first PR) · Electron · Changelog |

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

Team

Core team

<table> <tr> <td align="center" width="200"><a href="https://github.com/debpalash"><img src="https://github.com/debpalash.png?size=160" width="80" height="80" alt="Palash Debnath"></a><br><b>Palash Debnath</b><br><sub>Creator and Core Team</sub><br><sub><a href="https://palash.dev">palash.dev</a> · <a href="https://github.com/debpalash">GitHub</a> · <a href="https://x.com/idebpalash">X</a></sub></td> <td align="center" width="200"><a href="https://github.com/velixio"><img src="https://github.com/velixio.png?size=160" width="80" height="80" alt="Shimul Debnath"></a><br><b>Shimul Debnath</b><br><sub>Core Team</sub><br><sub><a href="https://shimul.me">shimul.me</a> · <a href="https://github.com/velixio">GitHub</a> · <a href="https://x.com/shimuldn">X</a></sub></td> </tr> </table>

Contributors

Thank you to everyone who has sent code, reports, translations and ideas. See all contributors · Contribute

License & responsible use

AGPL-3.0 covers the application, including commercial use under its conditions. Model weights, tokenizers, voices and generated-output conditions are separate; a paid app licence does not grant those rights. Clone voices only with permission. Model Manager now shows versioned model-source notices, evidence links and unresolved review gaps from the shared inventory. Its optional reviewed-file preview does not enforce ordinary downloads or certify commercial permission. See license details.