The new Gemini 1.5 Pro update adds the ability to listen to audio files and then process and extract text information from those audio clips. Gemini is capable of processing different types of audio into text, with many different languages to help users easily get the content they need. Below is a guide to converting audio to text on Gemini 1.5 Pro.
How to convert audio to text on Gemini 1.5 Pro
Step 1:
First you need to access Gemini's audio processing website at the link below.
Next, look at the Model section on the right and select Gemini 1.5 Pro to use.

Step 2:
Next, the user clicks on the Audio tab above to download the audio file they want to convert to text.

At this point, users will see options to upload audio to Gemini 1.5 Pro for use. You select Drive to upload audio from Google Drive.

At this point, the user needs to agree to let Google AI Studio access your Google account.

Step 3:
Users upload the audio file to be processed to Gemini 1.5 Pro, enter the request they want to perform , then click the blue circular send icon . Note that each account will have its own number of tokens and each time an audio file is uploaded, a different number of tokens will be needed to process the uploaded file.

Step 4:
Immediately after that, you will see the content converted from the audio on Gemini 1.5 Pro as shown below. The content is written in detail, specifically by hour for users to easily follow.

This new feature on Gemini 1.5 Pro applies to all Google accounts without you having to register anything else.