How to upload an audio file to Gemini-pro

Hi all,

I’ve tried several methods with Make to analyze a phone call with Gemini-pro, but I haven’t achieved satisfactory results! I based my approach on this template and added Google Cloud Storage with a bucket. It works, but the results aren’t as good as those from Google AI Studio.

In Google AI Studio, you can simply upload the audio file, and Gemini recognizes the text and responds to the prompt query.

Is there a way to achieve this using Make? How can I upload an audio file to Gemini-pro with Google Vertex AI to create a chat prompt?

Many thanks for your time,