登录

VoiceStudio

debpalashAGPL-3.0活跃维护

本地运行的 ElevenLabs 开源替代品，支持声音克隆、语音设计、视频配音、听写、转写和有声书制作，覆盖 646 种语言。

VoiceStudio is the open-source, fully-local ElevenLabs alternative — voice cloning, voice design, video dubbing, dictation, transcription & audiobook creation in 646 languages.

v0.5.7发布于 2026-10-26 14:59 UTC106,722star +3,598 / 7 天11,833fork同步于 2026-11-10 11:18 UTC
语音克隆语音合成视频配音语音转写有声书生成
对比 GitHub 官网aiaudiobookcudadubbingelevenlabs-alternative

怎么上手

由 README 提炼，执行前请确认
原文 
README 未提供命令行安装步骤，仅给出 GitHub Releases 下载入口
硬件要求按 README 说明

README 未给出具体显存或内存要求；支持笔记本、台式机、服务器、手机和平板运行，原生 GGUF 引擎在 AMD、Intel、NVIDIA GPU 上支持 Vulkan 加速。

纯 CPU 可运行支持 Apple Silicon需要 CUDA支持 ROCm / AMD有 Docker 镜像
下载：源码 zip·GitHub Releases（安装包）本站不镜像安装包

项目说明

由 README 自动翻译提炼
没人工点评？写下你的经验

本地运行的 ElevenLabs 开源替代，在一台机器上完成语音克隆、设计与配音

本地运行的 ElevenLabs 开源替代品，支持声音克隆、语音设计、视频配音、听写、转写和有声书制作，覆盖 646 种语言。

核心能力

  • 用一段干净参考录音克隆音色并合成语音
  • 用文字描述生成全新音色，无需录音样本
  • 翻译并配音视频，语音对齐原片时间轴
  • 内置悬浮听写组件与本地转写
  • 通过本地 API、MCP 与监视文件夹自动化任务

容易踩的坑

模型不随应用打包，需在 Model Manager 中按需下载；默认引擎为 k2-fsa/OmniVoice，换用其他引擎需另行选择并下载对应模型；Pro 为闭源构建且需账号，AGPL-3.0 版本才免费本地运行

内容由模型根据 README 生成，可能不完整或不准确，以官方文档为准。看原文 README

最近发版

5 个版本v0.5.7
全部 release
  1. ct2-rocm-4.8.4-78b1e17CTranslate2 4.8.4 HIP (Windows ROCm 10, RDNA 2)pre-release2026-11-09 · 2026-11-09 17:35 UTC
    查看更新说明

    Built by .github/workflows/ct2-rocm-windows.yml from OpenNMT/CTranslate2 78b1e1770fd3c28dbd125bbe586d90ae45e611b8 + cf4579017d089f49446edc59639f58d88ea79880 (tree 7d3ab96d381215943951607689fce10b32e192d8). Dependency asset for the opt-in Windows ROCm setup; not a VoiceStudio release.

  2. v0.5.8-beta.3v0.5.8-beta.3 — VoiceStudiopre-release2026-11-09 · 2026-11-09 11:41 UTC
    查看更新说明

    AMD and Intel GPUs now speed up OmniVoice, and setup gets far more forgiving. OmniVoice GGUF runs on AMD, Intel and NVIDIA GPUs through Vulkan on Windows and Linux, dots.tts arrives on Windows with no Python setup, and a failing PyTorch download or a broken GPU no longer leaves you without a working app.

    New since beta.2: updates now download in the background and install when you quit, with a title-bar pill for progress, Restart and Retry; Clone and Design render at best quality by default and offer faster settings only when a take is measured to be slow; you can run VoiceStudio on a Python you already have; model licence warnings clear once you accept the terms; and a more compact top bar.

    Download

    PlatformInstaller
    Windows x64Installer
    Windows ARM64 (experimental)Installer
    macOS Apple SiliconDMG
    macOS IntelDMG
    Linux x64AppImage · deb
    AndroidAPK · AAB
    iPhoneUnsigned IPA (sideload with your own Apple ID)

    Upgrading: Install over your existing app; voices, projects and settings are kept.

    Highlights

    • OmniVoice GGUF uses AMD, Intel and NVIDIA GPUs through Vulkan on Windows and Linux
    • dots.tts voice cloning now runs on Windows through audio.cpp, with no Python setup
    • Convert can keep your delivery, changing only the voice
    • Dubbing exports subtitles before dubbing and moves lines between speakers
    • Setup falls back to the CPU build when PyTorch downloads fail, and the app falls back to the CPU when the GPU fails

    Changed

    • Updates now download in the background and install when you quit, with a compact title-bar pill for progress, Restart and Retry, clearer error messages and a restart prompt when work is running (#3928)
    • The top bar is more compact: the account button is just your profile photo, or a person icon when signed out, and the GitHub star count is shortened (#3922).
    • Product analytics moved from PostHog to Supermetry, still only after a yes at the first-run prompt, and now also records which engine ran each generation and transcription. (#3902)
    • Restyled Settings → VoiceStudio account to match the home page: one account card with your plan and storage, the email shown once, and a storage bar visible at 0%. (#3885)
    • Account sign-in is available in every build, still off until you turn it on, and now starts on the VoiceStudio dashboard with a separate Sign up option (#3850)
    • The Pro page in the app now shows the correct $199 Lifetime price (#3831)
    • Mac releases use an Apple API key for notarization instead of an account password. (#3775) — thanks @velixio!
    • Source development now prepares the local API environment before launching Electron (#3637)
    • Remove obsolete screenshot and source-archive helpers that targeted the retired UI layout. (#3623)
    • Removed unused development tools (pytest-cov, Turborepo and a duplicate TypeScript) from the repository and fixed the remaining broken documentation l
  3. v0.5.8-beta.2v0.5.8-beta.2 — VoiceStudiopre-release2026-11-08 · 2026-11-08 21:13 UTC
    查看更新说明

    Installer signing

    PlatformSigning
    macOS (Apple Silicon)✅ Signed with Developer ID and notarized by Apple
    macOS (Intel)✅ Signed with Developer ID and notarized by Apple
    Windows x64⚠️ Unsigned: SmartScreen shows "Windows protected your PC"; choose More info → Run anyway
    Windows ARM64⚠️ Unsigned: SmartScreen shows "Windows protected your PC"; choose More info → Run anyway
    Linux x64— Linux packages are not code-signed

    Phone downloads

    Android: signed APK · Play bundle.

    iPhone: unsigned sideload IPA. Sign with your own Apple ID to install; this is not a TestFlight build.

    New since beta.1: an update prompt on every screen, including setup, that also works when GitHub downloads are down; setup shows the app version, your GPU and the build it will install, with help links always visible; a redesigned account page; opt-in analytics moved to Supermetry; clearer reports when the backend stops unexpectedly; five community fixes for dubbing, project bundles, IndexTTS seeds and health reporting; and PyTorch 2.10, which closes a checkpoint-loading security flaw (CVE-2026-24747).

    AMD and Intel GPUs now speed up OmniVoice, and setup gets far more forgiving. OmniVoice GGUF runs on AMD, Intel and NVIDIA GPUs through Vulkan on Windows and Linux, dots.tts arrives on Windows with no Python setup, and a failing PyTorch download or a broken GPU no longer leaves you without a working app.

    Download

    PlatformInstaller
    Windows x64Installer
    Windows ARM64 (experimental)Installer
    macOS Apple SiliconDMG
    macOS IntelDMG
    Linux x64AppImage · deb
    AndroidAPK · AAB
    iPhoneUnsigned IPA (sideload with your own Apple ID)

    Upgrading: Install over your existing app; voices, projects and settings are kept.

    Highlights

    • OmniVoice GGUF uses AMD, Intel and NVIDIA GPUs through Vulkan on Windows and Linux
    • dots.tts voice cloning now runs on Windows through audio.cpp, with no Python setup
    • Convert can keep your delivery, changing only the voice
    • Dubbing exports subtitles before dubbing and moves lines between speakers
    • Setup falls back to the CPU build when PyTorch downloads fail, and the app falls back to the CPU when the GPU fails

    Changed

    • Product analytics moved from PostHog to Supermetry, still only after a yes at the first-run prompt, and now also records which engine ran each generation and transcription. (#3902)
    • Restyled Settings → VoiceStudio account to match the home page: one account card with your plan and storage, the email shown once, and a st
  4. v0.5.8-beta.1v0.5.8-beta.1 — VoiceStudiopre-release2026-11-08 · 2026-11-08 14:50 UTC
    查看更新说明

    Installer signing

    PlatformSigning
    macOS (Apple Silicon)✅ Signed with Developer ID and notarized by Apple
    macOS (Intel)✅ Signed with Developer ID and notarized by Apple
    Windows x64⚠️ Unsigned: SmartScreen shows "Windows protected your PC"; choose More info → Run anyway
    Windows ARM64⚠️ Unsigned: SmartScreen shows "Windows protected your PC"; choose More info → Run anyway
    Linux x64— Linux packages are not code-signed

    Phone downloads

    Android: signed APK · Play bundle.

    iPhone: unsigned sideload IPA. Sign with your own Apple ID to install; this is not a TestFlight build.

    AMD and Intel GPUs now speed up OmniVoice, and setup gets far more forgiving. OmniVoice GGUF runs on AMD, Intel and NVIDIA GPUs through Vulkan on Windows and Linux, dots.tts arrives on Windows with no Python setup, and a failing PyTorch download or a broken GPU no longer leaves you without a working app.

    Download

    PlatformInstaller
    Windows x64Installer
    Windows ARM64 (experimental)Installer
    macOS Apple SiliconDMG
    macOS IntelDMG
    Linux x64AppImage · deb
    AndroidAPK · AAB
    iPhoneUnsigned IPA (sideload with your own Apple ID)

    Upgrading: Install over your existing app; voices, projects and settings are kept.

    Highlights

    • OmniVoice GGUF uses AMD, Intel and NVIDIA GPUs through Vulkan on Windows and Linux
    • dots.tts voice cloning now runs on Windows through audio.cpp, with no Python setup
    • Convert can keep your delivery, changing only the voice
    • Dubbing exports subtitles before dubbing and moves lines between speakers
    • Setup falls back to the CPU build when PyTorch downloads fail, and the app falls back to the CPU when the GPU fails

    Changed

    • Account sign-in is available in every build, still off until you turn it on, and now starts on the VoiceStudio dashboard with a separate Sign up option (#3850)
    • The Pro page in the app now shows the correct $199 Lifetime price (#3831)
    • Mac releases use an Apple API key for notarization instead of an account password. (#3775) — thanks @velixio!
    • Source development now prepares the local API environment before launching Electron (#3637)
    • Remove obsolete screenshot and source-archive helpers that targeted the retired UI layout. (#3623)
    • Removed unused development tools (pytest-cov, Turborepo and a duplicate TypeScript) from the repository and fixed the remaining broken documentation links (#3571, #2603, #2903) — thanks @themrbeasley and @marciok!
    • Workflows open at /workflows framed to their steps, Calls opens at /calls,
  5. v0.5.7v0.5.7 — VoiceStudio最新正式版2026-10-26 · 2026-10-26 14:59 UTC

    First, an apology. This release took much longer than it should have. Urgent family matters kept me away for a while, and I'm sorry for the wait and for the issues that sat unanswered meanwhile. Thank you for your patience and for every report, fix and kind word in the meantime.

    Welcome Shimul Debnath (velixio) to the core team. Shimul now helps maintain VoiceStudio — reviewing pull requests, triaging issues and keeping releases moving — so the project no longer waits on one person.

    VoiceStudio now runs on your phone and on PCs without a GPU, and the whole app is calmer. Preview iOS and Android apps run models on the phone itself, GPU-less computers get the small CPU PyTorch build, and the sidebar, Models, Dubbing, Stories and Workflows pages were redesigned around fewer, clearer controls.

    This release also adds an opt-in Beta update channel, a bottom player for takes, a GPU acceleration panel with honest Radeon reporting and the Ask VoiceStudio Agent, plus hundreds of fixes to cloning, dubbing, audiobooks, downloads and dictation.

    Download

    PlatformInstaller
    Windows x64Installer
    Windows ARM64 (experimental)Installer
    macOS Apple SiliconDMG
    macOS IntelDMG
    Linux x64AppImage · deb · Snap Store (sudo snap install voicestudio)
    AndroidAPK · AAB
    iPhoneSideload IPA — sign with your own Apple ID

    Upgrading: Install over your existing Electron app; voices, projects and settings are kept. If setup asks, choose Install local runtime to refresh its dependencies.

    • Remote compute devices, remote workers and GPU sharing moved to VoiceStudio Pro and are no longer in the open-source app; saved projects, voices and settings are unaffected (#2748)
    • Models without a plainly commercial licence, including the default OmniVoice model, ask you to accept their licence once in Model Catalogue; until then, API and MCP requests that use them return a licence error (#2689)
    • Docker, LAN or reverse-proxy access by a host name, without an API key or session, needs that name in OMNIVOICE_ALLOWED_HOSTS; IP addresses, localhost, *.ts.net and host.docker.internal work as before.
    • URL imports from servers on your own network need OMNIVOICE_ALLOW_PRIVATE_URL_IMPORTS=1.
    • Where to set these variables: a line in ~/.config/omnivoice/env (macOS, Linux) or %USERPROFILE%\.config\omnivoice\env (Windows) for the desktop app, -e for Docker.

    Moving from Tauri: Close the app, back up its data directory, install Electron, and verify your voices and projects before removing Tauri. Follow the migration guide. Tauri v0.5.3 remains the final Tauri release; its updater cannot install Electron.

    Installer trust: macOS installers are signed. Windows installers are not code-signed yet, so SmartScreen may

用户点评

登录用户的真实使用记录，可按版本和硬件筛选
共 0 条

    还没有人点评。第一个说出真实体验的人最有价值。

    README 原文

    未翻译
    在 GitHub 打开

    What you can do

    • 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

    Start with VoiceStudio (default, powered by k2-fsa/OmniVoice), or pick from dozens of other engines in the Model Manager. See the features & engine catalog.

    Pro and Cloud

    Everything above is free, runs on your own hardware and needs no account. Pro and Cloud are optional.

    Platforms

    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.

    Stable · Apple SiliconmacOS 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

    Download the DMG for your Mac, open it and drag VoiceStudio into Applications.

    Download · Guide

    curl -fsSL https://voicestudio.sh/install | sh

    The app UI runs on Intel; connect it to a VoiceStudio backend on another computer.

    Guide

    [!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.

    Stable · x64Windows 10/11 x64 · NVIDIA CUDA · AMD ROCm (opt-in) · CPU.

    irm https://voicestudio.sh/install.ps1 | iex

    Download the Windows installer · Guide · AMD ROCm

    Native app UI; the x64 Python backend runs under emulation on the CPU.

    Download · Guide

    Stable · x64Linux x64 · NVIDIA CUDA · CPU · Vulkan for supported GGUF engines.

    curl -fsSL https://voicestudio.sh/install | sh


    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:

    Download

    sudo apt install ./VoiceStudio-*-linux-x64.deb

    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:

    Download

    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

    Guide

    Guide

    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 10+ · Preview · On-device, offline after model download.

    Download APK · Guide

    Add this repository in an F-Droid-compatible client; verify the fingerprint in the guide.

    https://debpalash.github.io/VoiceStudio/fdroid/repo

    Guide

    Add this source in Obtainium, or import the provided configuration.

    https://github.com/debpalash/VoiceStudio

    Import configuration

    adb install -r VoiceStudio-*-android.apk

    iOS / iPadOS 17+ · Preview · On-device, offline after model download.

    Download the IPA and follow the signing and sideloading instructions.

    Download · Guide

    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.

    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

    If 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 dev

    bun 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.md

    Upgrading from 0.5.3 or older (the Tauri app)? Install the new app separately.

    Documentation

    All guides

    NeedStart here
    Setup helpTroubleshooting · Model downloads
    GuidesMulti-speaker dubbing · Expressive speech · Exporting dubs
    Models & qualityEngine guides · whisper.cpp ASR · Benchmarks
    IntegrationsLocal API · MCP · Examples
    Phone appsiOS and Android
    DevelopmentContributing (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].

    Ko-fi · PayPal · Tiers and benefits · Get your logo listed

    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.

    More projects: debpalash · velixio

    Team

    Core team

    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

    相关项目

    同分类里 star 最高的项目
    对比全部 →
    voicebox
    jamiepine·Python

    开源 AI 语音工作室，支持声音克隆、语音听写和语音生成，基于 Qwen3-TTS 与 Whisper，可在 CUDA 或 MLX 上本地运行。

    语音克隆+4语音推理
    60349+5967.6kv0.5.02026-10-07 01:17 UTC
    whisper.cpp
    ggml-org·C++

    OpenAI Whisper 语音识别模型的 C/C++ 移植版，无需 Python 和 GPU 依赖，在普通 CPU 上就能跑语音转文字。

    语音识别+4语音推理
    55060+736.3kv1.9.52026-11-10 08:39 UTC
    faster-whisper
    SYSTRAN·Python

    基于 CTranslate2 重实现的 Whisper 语音转文字推理引擎，通过量化与高效推理大幅提速并降低显存占用，适合本地部署转录。

    语音识别+4语音推理
    26639+672.2kv1.2.12026-11-10 10:13 UTC
    whisperX
    m-bain·Python

    基于 Whisper 的语音识别工具，能给出词级时间戳并支持说话人分离，适合做字幕对齐和会议转写。

    语音识别+4语音推理
    25193+462.5kv3.8.62026-10-22 14:53 UTC