Google announces two new Gemini features

Google launches a new feature for those who love (and create) Podcast. It is called Audio Ovserview and is implemented inside its Assyssing Ai, Gemini. It allows to transform documents, presentations and reports into audio content, rich in discussions and dialogues between two phantom presenters (hosts). The goal is to make information more accessible and engaging, allowing users to listen to synthesis of their materials while they are in motion as if they were discussed on the radio or inside already known containers.

How audio ovview works

  • One: the loading of content.Users can load documents or presentations on various topics within Gemini.
  • Two: Generation of audio.Once the file is uploaded, Gemini creates a conversation between two ai hosts that discuss and summarize the contents of the document, offering an in -depth and engaging overview.
  • Accessibility: The generated discussions can be listened to both on the web and through the Gemini mobile app. You can share or download the audio for listening offline.

Currently, the Ovserview audio function is available for subscribers to Gemini and Gemini Advanced globally in English, with the intention of supporting further languages ​​in the future. In short, for the Italians it will still take some time. ​

A second news

In addition to Audio Ovserview, Google also presented Canvas an interactive space designed to simplify the creation, modification and sharing of documents and code in real time. Users can generate drafts and then ask Gemini to analyze them and improve them by adapting the tone, length, formatting. In addition, Google says, supports quick prototyping for developers, facilitating the creation of initial versions of projects such as web apps, Python scripts, games and simulations.

By Editor

One thought on “Google announces two new Gemini features”

Leave a Reply