为什么值得关注

它结合了隐私优先的设计（无麦克风、无网络）、基于进程的音频捕获以及丰富的角色动画系统，并采用 MIT 开源许可，支持 Linux、Windows 和 macOS。

适合谁使用

构建语音交互桌面应用的开发者
希望为直播或视频通话添加动态角色的主播和内容创作者
在语音通话或专注工作时想要视觉陪伴的用户
探索从系统音频驱动实时 3D 角色的爱好者

典型使用场景

用角色动画可视化语音助手的回应
为直播或视频通话添加一个反应式虚拟形象
在桌面上创建一个不干扰工作的氛围角色
开发和测试自定义 VRM/VRMA 角色集成

项目优势

跨平台构建（Linux、Windows、macOS），支持原生音频捕获
隐私安全：不访问麦克风，不录制音频，不传输网络数据
支持多种生动的动画（空闲、说话、问候、庆祝、跳舞）通过 VRMA 文件
采用 MIT 开源许可，并提供清晰的资产替换流程以便分发

使用前须知

需要 Node.js 24+、硬件加速图形以及特定操作系统版本（Windows 20348+、macOS 14.2+）
角色媒体文件不包含在仓库中，发布前必须替换并妥善管理许可
窗口不含内置控制按钮（需通过窗口管理器关闭/最小化），仅捕获播放音频，不捕获麦克风输入

README 快速开始

Persona

Persona brings an expressive character to realtime voice conversations.

It is a cross-platform desktop experience that gives voice interactions a recognizable visual identity alongside your work.

Platform support

Platform	Automatic voice output listener	Distribution
Linux	PipeWire process-stream capture	AppImage and DEB
Windows	WASAPI process-loopback capture	NSIS installer
macOS 14.2+	Core Audio process tap	DMG and ZIP, arm64 and x64

Linux requires pw-dump and pw-record on PATH. Windows process-loopback requires Windows 10 build 20348 or newer. macOS asks once for System Audio Recording permission.

Each listener is scoped to the supported application's playback process. Persona does not capture the microphone, save audio, produce speech, transcribe content, or send audio over the network.

Try Persona locally

Requirements:

Node.js 24 or newer
npm
A desktop session with hardware-accelerated graphics

Character media is not part of the repository. Before launching, place local test media or redistributable media in the exact slots documented below.

npm install
npm run demo

Demo mode drives the production character view with a synthetic level. To run normal automatic detection:

npm run build
npm start

For a background launch:

npm start -- --background

The window intentionally contains no controls:

Scroll to zoom.
Left-drag to orbit.
Right-drag to pan.
Use your window manager's move gesture to reposition the window.

On Hyprland, Persona also applies floating, pinned, topmost, full-opacity, no-blur, no-shadow, and decoration-free properties. macOS uses an all-Spaces topmost window. Other desktops use the strongest supported Electron window hints.

Build native packages

Build on the operating system you are targeting:

npm run dist:linux
npm run dist:windows
npm run dist:mac

Outputs are written to release/. Windows needs Visual Studio Build Tools with the C++ desktop workload. macOS needs Xcode Command Line Tools and macOS 14.2+ SDK support.

GitHub Actions runs the full JavaScript, renderer, native compile, and native self-test suite on Linux, Windows, and macOS. Prerelease tags shaped like v0.1.0-beta.0 create native packages and a checksum file, but only after the asset release gate passes. See [Releas

项目描述

Bringing real-time voice to life.

persona