amica

semperaiMIT活跃维护

开源 3D 虚拟角色交互界面,集成语音合成与语音识别,让用户通过自然对话与 3D 角色实时交流。

Amica is an open source interface for interactive communication with 3D characters with voice synthesis and speech recognition.

app-v0.2.1发布于 2023-12-23 22:11 UTC1,620star275fork同步于 2026-11-07 07:30 UTC

怎么上手

由 README 提炼,执行前请确认
git clone [email protected]:semperai/amica.git
npm install
npm run dev
硬件要求按 README 说明

README 未说明具体显存或 GPU 型号要求;本地模型推理的硬件需求取决于所选后端(如 llama.cpp、Coqui),前端本身在浏览器中运行

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

开源 3D 虚拟角色交互界面,支持语音合成与语音识别,可接入多种 AI 后端

开源 3D 虚拟角色交互界面,集成语音合成与语音识别,让用户通过自然对话与 3D 角色实时交流。

核心能力

  • 用 three.js 与 three-vrm 渲染可导入的 VRM 3D 角色
  • 集成 Whisper 语音识别与 Silero VAD 语音活动检测
  • 支持 ElevenLabs、Speech T5、Coqui 等多种 TTS 后端
  • 可对接 llama.cpp、Ollama、OpenAI、OpenRouter 等聊天后端
  • 内置情绪引擎,让角色在回复中表达情感

容易踩的坑

配置主要在 .env.local 中完成,需参照 config.ts 填写;使用 OpenRouter 等云端后端需自备 API Key;Windows 用户安装时建议新建独立文件夹,避免卸载时误删其他文件

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

4 个版本app-v0.2.1
  1. app-v0.2.1Amica v0.2.1pre-release最新正式版2023-12-23 · 2023-12-23 22:11 UTC

    Amica 0.2.1

    This patch release of Amica includes fixes for macOS Microphone and WebCam support, as well as improved Ollama implementation, and initial Docker setup.

    Thank you

    @andyccliao @Yvonne-Aizawa @dreamjz

    Download Notes

    • .dmg is for macOS
    • .app.tar.gz is for macOS
    • .exe is for Windows
    • .msi is for Windows
    • .AppImage is for any Linux 64 bit
      • Note: Be sure to set this to executable to run it (chmod +x)
    • .deb is for Debian (or Ubuntu) distributions
  2. app-v0.2.0Amica v0.2.0pre-release2023-12-16 · 2023-12-16 01:56 UTC
    查看更新说明

    Amica 0.2.0

    This release of Amica includes desktop builds for Mac, Windows, and Linux. It also supports sharing and importing characters.

    New features

    • Share and import characters
    • Support for loading Mixamo animations
    • Added button to mute TTS temporarily
    • Added button to toggle unrestricted message size
    • Add support for Ollama vision
    • Add support for KoboldAI
    • Add whisper.cpp STT backend
    • Add support for OpenAI TTS
    • Add i18n support
    • Added docs site https://docs.heyamica.com/
    • Added ability to change background color
    • Added ability for background to be transparent
    • Added ability to change name
    • Added notification for network errors

    Bug fixes

    • Fix VAD error: "The object can not be found"
    • Fix loading VRM, stop previous animation before starting newly loaded * Fix vision_llama backend page selector
    • Fix OpenAI TTS link
    • Fix removal of non-ascii characters
    • Prune emojis from TTS
    • Prompt to reload if background video changed
    • Fix mobile layout

    Miscellaneous

    • Improved default system prompt
    • Redesigned the UI
    • Refactor settings page
    • Basic test setup

    Thank you

    • @Aspie96
    • @morphles
    • @PatrickLearn
    • @snowyu

    Download Notes

    • .dmg is for macOS
    • .app.tar.gz is for macOS
    • .exe is for Windows
    • .msi is for Windows
    • .AppImage is for any Linux 64 bit
      • Note: Be sure to set this to executable to run it (chmod +x)
    • .deb is for Debian (or Ubuntu) distributions
  3. app-v0.1.2Amica v0.1.2pre-release2023-12-15 · 2023-12-15 03:16 UTC
    查看更新说明

    Amica 0.1.2

    This supports Ollama vision api (such as llava). Try by running ollama run llava and configure vision to use.

    Download Notes

    • .dmg is for macOS
    • .app.tar.gz is for macOS
    • .exe is for Windows
    • .msi is for Windows
    • .AppImage is for any Linux 64 bit
      • Note: Be sure to set this to executable to run it (chmod +x)
    • .deb is for Debian (or Ubuntu) distributions
  4. app-v0.1.1Amica v0.1.1pre-release2023-12-15 · 2023-12-15 02:29 UTC
    查看更新说明

    Amica 0.1.1

    This is the first release using https://tauri.app/ - this should be considered a preview release.

    Download Notes

    • .dmg is for macOS
    • .app.tar.gz is for macOS
    • .exe is for Windows
    • .msi is for Windows
    • .AppImage is for any Linux 64 bit
      • Note: Be sure to set this to executable to run it (chmod +x)
    • .deb is for Debian (or Ubuntu) distributions

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

    twitter License Hits GitHub issues GitHub closed issues

    Amica allows you to converse with highly customizable 3D characters that can communicate via natural voice chat and vision, with an emotion engine that allows Amica to express feelings and more. Customize her any way you want with any AI technology.

    Try Amica here on mobile, tablet or desktop

    For Windows Users: Please create a new folder for Amica during installation to prevent the unintentional deletion of other files during uninstallation.

    We just released Amica 1.2 with lots of new features. Docs will be further updated soon, watch the video to learn about what Amica 1.2 offers:

    Video Title

    You can import VRM files, adjust the voice to fit the character, and generate response text that includes emotional expressions.

    The various features of Amica mainly use and support the following technologies:

    To see tutorials on configuring any of these with Amica please visit the official Amica documentation.

    🛠️ Installation and running

    To run this project locally, clone or download the repository.

    git clone [email protected]:semperai/amica.git
    

    Install the required packages.

    npm install
    

    After installing the packages, start the development web server using the following command:

    npm run dev
    

    Once started, please visit the following URL to confirm that it is working properly.

    http://localhost:3000

    📝 Configuration

    Most of the configuration is done in the .env.local file. Reference the config.ts file for the available options.

    OpenRouter Configuration

    To use OpenRouter as a chat backend, set the following environment variables in your .env.local file:

    • NEXT_PUBLIC_OPENROUTER_APIKEY: Your OpenRouter API key (required)
    • NEXT_PUBLIC_OPENROUTER_URL: Custom OpenRouter API URL (optional, defaults to https://openrouter.ai/api/v1)
    • NEXT_PUBLIC_OPENROUTER_MODEL: Default OpenRouter model (optional, defaults to openai/gpt-3.5-turbo)
    amica
    ├── .env.local
    ├── src
    │   ├── utils
    │   │   └── config.ts
    

    📦 Desktop Application

    Amica uses Tauri to build the desktop application.

    To develop the desktop application, use the following command:

    npm run tauri dev
    

    📖 Documentation

    View the documentation for more information on how to configure and use Amica.

    📜 History

    This project originated as a fork of ChatVRM by Pixiv:

    https://pixiv.github.io/ChatVRM

    🔒 License

    • The majority of this project is released under the MIT license as found in the LICENSE file.
    • Assets such as 3D models and images are released under their authors respective licenses.

    ✨ Star History

    Star History

    🤗 Contributors