Wunjo AI：创新科技文本合成语音，打造deepfake动画视频！

文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

Wunjo AI是一个从文本，语音识别到文本的语音合成，并创建深度伪造动画。与类似的Web应用程序不同，该应用程序的独特功能之一是能够创建具有多种声音的多对话，并且使用的字符数不受限制。您还可以实时朗读文本，应用程序将从音频中识别它。此功能非常适合听写文本而不是手动键入文本。文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

总而言之，这个神经网络桌面应用程序对于需要语音合成、语音到文本识别和创建 deepfake 动画的任何人来说都是一个方便而强大的工具。最重要的是，该应用程序是免费的，在本地安装，并且易于使用！您可以在广告、书籍、游戏等的配音中使用它。文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

官网

https://wladradchenko.ru/wunjo文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

设置

需要 3.8 <= Python <=3.10 和 ffmpeg。文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

创建 venv 并激活它们：文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

python -m venv venvsource venv/bin/activate

安装依赖项：文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

pip install -r requirements.txt

注意力！首次运行视频合成时，模型将下载到大小为 5GB 的 .wunja/talker/checkpoints 和 .wunja/talker/gfpgan 中。这可能需要很长时间。文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

转到便携式文件夹文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

cd portable

跑：文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

briefcase dev

此外，还可以创建生成：文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

briefcase build

运行构建文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

briefcase run

为您的操作系统创建安装包：文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

briefcase package

扩展

该程序的功能可以通过自定义扩展进行补充。文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

链接https://wladradchenko.ru/static/wunjo.wladradchenko.ru/extensions.json中的可用扩展列表。文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

安装数据包

Ubuntu / Debian Stable v1.2 ：https://wladradchenko.ru/static/wunjo.wladradchenko.ru/build/linux/wunjo_1.2.0.deb文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

Ubuntu / Debian Extensions v1.3 ：https://wladradchenko.ru/static/wunjo.wladradchenko.ru/build/linux/wunjo_1.3.1.deb文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

// Requirement to create animation is ffmpeg
sudo apt install ffmpeg

// Install app
sudo dpkg -i wunjo_{vesrion}.deb

// Attention! The first time you run video synthesis, models will be downloaded in .wunja/talker/checkpoints and .wunja/talker/gfpgan in size 5GB. This may take a long time.

// Remove app
sudo dpkg -r wunjo

// Remove cache
rm -rf ~/.wunjo

MacOS 稳定版 v1.2 ： https://wladradchenko.ru/static/wunjo.wladradchenko.ru/build/macos/wunjo_macos_1.2.0.zip文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

MacOS 扩展 v1.3 ：https://wladradchenko.ru/static/wunjo.wladradchenko.ru/build/macos/wunjo_macos_1.3.1.zip文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

// Requirement to create animation is ffmpeg
brew install ffmpeg 

// Unzip app
unzip wunjo_macos_{vesrion}.zip

// Attention! The first time you run video synthesis, models will be downloaded in .wunja/talker/checkpoints and .wunja/talker/gfpgan in size 5GB. This may take a long time.

// Remove cache
rm -rf ~/.wunjo

WIN v1.3 ：https://wladradchenko.ru/static/wunjo.wladradchenko.ru/build/windows/wunjo_1.3.2.msi文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html

// Requirement to create animation is ffmpeg, Install ffmpeg and add to Path env
setx PATH "%PATH%;C:\path\to\ffmpeg\bin"

// Install app
wunjo_{vesrion}.msi

// Important! How to set up deepfake for Windows. You need to give permission to read the neural network models in the gfpgan folder after the models are installed! Without this setting, the result of deepfake generation will be "Face not found".

icacls "%USERPROFILE%/.wunjo/deepfake/gfpgan/weights/*.pth" /grant:r "Users":(R,W)

// Attention! The first time you run video synthesis, models will be downloaded in .wunja/talker/checkpoints and .wunja/talker/gfpgan in size 5GB. This may take a long time.

//Remove cache
%USERPROFILE%/.wunjo

诺一斯 NOISE宝藏阁文章源自菜鸟学院-https://www.cainiaoxueyuan.com/office/56102.html