In this application, I utilized the OpenAI API to convert text into audio. The backend functions as a mechanism that extracts the voice name and text from the request body. The frontend comprises a page where users can select their preferred voice, a text field for inputting the text to be transformed into audio, and an audio playback option for listening.
- Clone the repository using the following command:
git clone https://github.com/rafaelmerlotto/openai_voice_app
- Install NPM packges:
npm install
- Create a file named
.env, in this file create three environment variables:
OPENAI_API_KEY
To get the API key, you need to visit the website: https://openai.com/blog/openai-api
- for run this app, you need on both directories frontend and server execute the command:
npm start
- Rafael Merlotto
