Update

V3.0 Now not only supports Japanese TTS using VoiceVox. But also supports TTS for RU (Russian), EN (English), DE (German), ES (Spanish), FR (French), TT (Tatar), UA (Ukrainian), UZ (Uzbek), XAL (Kalmyk), Indic (Hindi), using Seliro TTS. Change voicevox_tts on run.py to seliro_tts, for detailed information of how to use Seliro TTS

AI Waifu Vtuber & Assistant

This project is inspired by shioridotdev and utilizes various technologies such as VoiceVox Engine, DeepL, Whisper OpenAI, Seliro TTS and VtubeStudio to create an AI waifu virtual YouTuber.

Demo

• Demo
• Live Test
• Code Explain

Technologies Used

• VoiceVox Engine
• DeepL
• Whisper OpenAI
• Seliro TTS
• VB-Cable
• VtubeStudio

Installation

You must use your own OpenAI and DeepL API KEY

To use this project, you will need to download the VoiceVox Engine from their GitHub page. You will also need to capture desktop audio using Virtual Cable and use it as input on VtubeStudio microphone.

Use chat.txt and output.txt as an input on OBS Text (Realtime Caption)

I also write the explanation inside the code

Credits

This project is inspired by the work of shioridotdev. Special thanks to the creators of the technologies used in this project including VoiceVox Engine, DeepL, Whisper OpenAI, and VtubeStudio.