Google has recently improved its Gemini AI model with an exciting new capability called the Audio Overview. This innovative feature allows users to convert various types of documents, slides, and reports into engaging audio discussions featuring two AI hosts, embracing a podcast-like format.
How to Generate Audio Overviews in Google Gemini
To kick off your audio transformation journey, directly navigate to the Gemini website or open the corresponding app. Look for the ‘+’ icon, located right beside the Deep Research button, and click on it to choose Files.
It’s important to note that Gemini supports a wide array of file formats, which include standard text documents like .DOC and .PDF, as well as data representations such as .CSV. If you are working with coding files, like .PHP or .JAVA, you may need the Gemini Advanced version.
After your file has been uploaded and processed, you’ll notice a new button labeled Generate Audio Overview. Click this to initiate the generation process.
The creation of your Audio Overview may take a few minutes, depending on your document’s length. Don’t worry—you can continue working in the chat window or even exit Gemini while you wait!
Once ready, a notification will surface on your PC or mobile—provided you’ve enabled notifications from the Gemini website—for you to start enjoying your audio content.
To listen to your audio overview, simply hit the Play button on the media player. Gemini’s audio player offers handy features such as a progress bar for easy navigation, 10-second forward and backward buttons, plus speed adjustment options for your listening preference.
If you’re utilizing the Gemini app, tap the Plus button to add your desired file for transformation.
After your chosen file is uploaded, press the Generate Audio Overview button that appears.
Once the Audio Overview is created, click on the produced output. This will guide you to your default browser, where the Audio Player will be available for you to press Play and commence listening.
Currently, please note that playing Audio Overviews directly within the app is unsupported.
Sharing and Downloading Your Audio Overviews
Your newly generated podcast is ready to be shared or stored for future listening. To share, click on the Overflow Menu (three dots) and select Share Conversation.
A pop-up will appear; simply copy the resulting shareable link and distribute it wherever you like.
If you wish to enjoy the audio offline, downloading your Audio Overview is straightforward. Select the Download button in the Overflow Menu, and the download process will commence instantly.
The Audio Overviews feature from Google Gemini is a brilliant tool for anyone handling large volumes of information. As the functionality of Gemini evolves, consider exploring its extensions to enhance your productivity even further.
Image credit: Unsplash. All screenshots by Jay Kakade.
Frequently Asked Questions
1. What types of files can I upload to generate Audio Overviews in Google Gemini?
You can upload various file types including. DOC, .PDF, and. CSV. If you’re looking to work with programming files like. PHP or. JAVA, you’ll need Gemini Advanced.
2. How do I share my Audio Overview with others?
To share your Audio Overview, simply click on the Overflow Menu (three dots), select ‘Share Conversation, ’ and copy the shareable link provided.
3. Can I play my Audio Overview directly within the Gemini app?
No, currently the Audio Overview cannot be played directly within the app. It will redirect you to your default browser where you can access the audio player.
Leave a Reply ▼