Kuebiko

WARNING: This doc is out of date, while it still applies to the legacy mode, I recommend using the Streamer.bot and Speaker.bot Mode instead. If needed a Tutorial will be added, however until then, there will be dragons. You will need to create a custom system prompt, it is recommended to read up on prompt engineering and trying out a lot.

A Twitch Chat Bot that reads twitch chat and creates a text to speech response using google could api and openai's GPT-3 text completion model.
Explore the docs »

View Demo · Report Bug · Request Feature

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Roadmap
5. Contributing
6. License
7. Contact
8. Acknowledgments

YouTube Videl Tutorial !OUTDATED!

This is a project to setup your very own VTuber AI similar to "Neuro-Sama".

(back to top)

Built With

• Python

(back to top)

Getting Started

This is an example of how you may give instructions on setting up your project locally. To get a local copy up and running follow these simple example steps.

Prerequisites

• VLC MUST BE DOWNLOADED ON YOUR COMPUTER

In order to install the prerequisites you will need to do:

• Install poetry

• poetry install

Installation

1. Get a OpenAI API Key at OpenAPIKey

2. Get a Twitch API Token at TwitchToken

3. Create a Google Cloud Project with TTS Service enabled and download JSON credentials file. GoogleCloud

4. Clone the repo

   git clone https://github.com/adi-panda/Kuebiko/

5. Add the Google Cloud JSON file into the project folder.

6. Rename .env.example to .env and enter API Keys:

   TWITCH_CHANNEL="You're Twitch Token"
   TWITCH_TOKEN="Your TWITCH Channel Name"
   OPENAI_API_KEY="Your OpenAI API Key"
   GOOGLE_JSON_PATH="Your Google Cloud JSON Path"
   BOT_NAME="Neuro-Sama"
   ELEVENLABS_APIKEY="Your ElevenLabs API Key"
   ELEVENLABS_VOICEID="Your ElevenLabs Voice Id"
   WEBSOCKET_URL="Your WebSocket Url"

7. Download VTube Studio and use VBAudio Cable to route audio coming from the program.

8. Add the following script into OBS CaptionsScript

9. Create a new text source for captions, and set it to read from a file, select the subtitle.txt file from the project folder.

10. In the script options put the name of you're text source.

11. Set the script in transform options to scale to inner bounds, and adjust the size of the captions.

12. Enjoy! For more details watch the attatched video.

13. IN ORDER TO CHANGE THE VOICE OF YOU'RE VTUBER you will need to change the following parameters in main.py Here is a list of supported voices

      voice = texttospeech.VoiceSelectionParams(
          language_code="en-GB",
          name= "en-GB-Wavenet-B",
          ssml_gender=texttospeech.SsmlVoiceGender.MALE,
      )

14. Run

    poetry run python main.py

(back to top)

Usage

Use this space to show useful examples of how a project can be used. Additional screenshots, code examples and demos work well in this space. You may also link to more resources.

For more examples, please refer to the Documentation

(back to top)

Roadmap

• Local LLama Support to remove the need for OpenAI and the associated restrictions

See the open issues for a full list of proposed features (and known issues).

(back to top)

Contributing

Contributions are what make the open source community such an amazing place to learn, inspire, and create. Any contributions you make are greatly appreciated.

If you have a suggestion that would make this better, please fork the repo and create a pull request. You can also simply open an issue with the tag "enhancement". Don't forget to give the project a star! Thanks again!

1. Fork the Project
2. Create your Feature Branch (git checkout -b feature/AmazingFeature)
3. Commit your Changes (git commit -m 'Add some AmazingFeature')
4. Push to the Branch (git push origin feature/AmazingFeature)
5. Open a Pull Request

(back to top)

License

Distributed under the MIT License.

(back to top)

Contact

@adi_panda - hello(aṭ)adipanda.me
@caesarlp - realcaesarlp(aṭ)gmail.com

Project Link: You are here

(back to top)

Acknowledgments

(back to top)

Instructions

Replace API Keys in code and add google cloud json file and program should work!