AI based search and Image generation with voice prompt in 55+ language.
This is a web application that uses AI to generate chat responses and images based on user requests. The application is built using Express and Node.js, and uses OpenAI's Whisper API for voice transcription, GPT-3.5 Turbo for chat completion, and DALL-E for image generation.
To install and run this application on your local machine, follow these steps:
-
Clone this repository to your local machine using the following command:
git clone https://github.com/your-username/your-project-name.git
-
Install the necessary dependencies by running the following command in the root directory of the project:
yarn install
-
Create a
.env
file in the root directory of the project and add the following environment variables:OPENAI_API_KEY=your_openai_api_key
Replace
your_openai_api_key
with your OpenAI API key. -
Start the application by running the following command:
yarn start
This will start the server on port 3000.
To use the application, follow these steps:
-
Navigate to
http://localhost:3000
in your web browser. -
Click on the microphone icon to enable voice recognition.
-
Speak your request into the microphone. The application will transcribe your request using OpenAI's Whisper API.
-
Depending on your request, the application will either generate a chat response or an image using GPT-3.5 Turbo and DALL-E, respectively.
-
The application will display the generated chat response or image on the screen.
If you'd like to contribute to this project, please follow these guidelines:
-
Fork the repository and create a new branch for your feature or bug fix.
-
Make your changes and test them thoroughly.
-
Create a pull request and provide a clear description of your changes.
-
Wait for feedback and make any necessary changes.