RizzGPT and FashionGPT Web Service is a web application that allows users to upload videos to receive humorous or fashion-related descriptions and voiceovers. The project integrates OpenAI's GPT-4 for generating descriptions and their text-to-speech engine to produce voiceovers.
- RizzGPT Mode: Provides a humorous roast of the person in the video focusing on their fashion.
- FashionGPT Mode: Offers fashion advice in a friendly manner to the person in the video.
- Video Upload: Users can upload a video file to be processed.
- Voiceover Generation: Generates an audio file with the voiceover based on the GPT-4 descriptions.
Before you begin, ensure you have met the following requirements:
- Node.js (at least version 14.x)
- npm (usually comes with Node.js)
- An API key from OpenAI
Follow these steps to set up RizzGPT and FashionGPT Web Service on your local machine:
- Clone the repository:
git clone [https://github.com/your-username/rizzgpt-fashiongpt-service.git](https://github.com/Arbaaz-Mahmood/Rizz-GPT.git)- Navigate to the project directory:
cd Rizz-GPT- Install the required npm packages:
npm installDownload the FFMPEG binaries from https://ffmpeg.org/download.html and add the /bin folder to the system's PATH environment variable.
You can install FFMPEG using Homebrew:
brew install ffmpegYou can install FFMPEG from the package manager:
sudo apt update
sudo apt install ffmpeg- Set your OpenAI API key in
index.js:
const openaiApiKey = `your-openai-api-key`;- (Optional) Customize configurations such as the port number in
index.jsif you have specific requirements or are deploying the service.
To start the application, run the following command in the project directory:
npm startBy default, the server will start on http://localhost:3000. You can access the web application through any web browser by visiting this URL.
Once the application is running, use it as follows:
- Select either the RizzGPT or the FashionGPT mode by clicking the corresponding button.
- Upload a video file by clicking the "Upload" button.
- Wait for the processing to complete. The progress will be indicated on the web page.
- Once processing finishes, you can listen to the generated voiceover directly on the web page or start a new upload.
Contributions, issues, and feature requests are welcome.
This project is licensed under the MIT License.
If you have any questions or comments about this project, please feel free to contact the maintainer via twitter DMs @hingumtringum or email at: am1381@student.london.ac.uk