Audio to Text using Python and OpenAI

In this tutorial, we will create a simple app that uses the OpenAI Whisper API to transcribe audio files to text. We will use the Python library "pydub" for audio manipulation and "python-dotenv" to securely store our OpenAI API key. First, clone the repository and install the required libraries. Then, set up your OpenAI API key and save it in a .env file. The code includes two main functions: convert_to_mono_16k to convert audio files to mono and 16kHz, and transcribe_audio to transcribe the audio to text using Whisper. Finally, test the code with a sample audio file and check the output text in the terminal.