Since ChatGPT was released, I've always wanted to be able to input queries by speaking instead of typing.

It just seems like it would be a much more natural way to interact with the system.

So here's a simple python script that leverages the ChatGPT and Whisper APIs to provide an experience similar to the ChatGPT web interface, but with audio input instead of text.

It works like this:

User: [Recording. Press the enter button to stop.] Hello?

Assistant: Hello! How can I assist you today?

User: [Recording. Press the enter button to stop.] How are you today?

Assistant: As an AI language model, I don't have feelings or emotions. But I'm always ready to assist you with any questions you may have!