Google added a very remarkable feature to its artificial intelligence Gemini: The ability to listen to and summarize audio files. This feature has a structure that can be used to convert voice recordings into text or summarize them.
This new feature is not currently available to everyone; It can only be tried within the scope of the Gemini 1.5 Pro plan, which is still in the testing phase. Users can listen to audio files they download from an external source with Gemini and get help to achieve the result they want.
Google Gemini can understand the voice it listens to and act according to the user's demands. In this way, functions such as converting an audio file into words or creating a summary are among Gemini's capabilities.
The Gemini 1.5 Pro feature currently requires the use of Vertex AI or AI Studio, Google's development platforms. It remains unclear whether the feature will be exclusive to these platforms or will reach all users.