Home

Welcome to the Wunjo Wiki

Overview

Wunjo is a neural network desktop application specializing in:

• Speech Synthesis
• Voice-to-Text Recognition
• Voice Clone
• Deepfake Face Animation Creation
• Deepfake Mouth Animation Creation
• Deepfake Swap Face
• Deepfake Face Emotion Animation Creation
• Video to Video by Text Prompt
• Segment Anything

Unlike similar web applications, Wunjo allows for multi-dialogues with multiple voices without a character limit. You can also convert spoken text to written text in real-time, making it useful for dictation.

You will find help information about Wunjo AI on multi languages in wiki on English, Русском, 中文.

👉 Use Cases: Voice acting for commercials, content, books, games, and more!

Getting Started

Requirements

• Python 3.10
• FFmpeg

Installation Steps

1. Create and activate a virtual environment:

   python -m venv venv
   source venv/bin/activate
   

2. Install dependencies:

   // CPU
   pip install -r requirements_cpu.txt  // Not MacOS
   // CPU only MacOS
   pip install -r requirements_macos.txt
   // GPU
   pip install -r requirements_gpu.txt  // Not MacOS
   

More information about installation in How to install the application and How to use the GPU in the application.

🚨 Heads Up!: The first run each feature will download models of size around 1GB-10GB from application. This may take time.

Contact Information

• Owner: Wladislav Radchenko
• Email: i@wladradchenko.ru