Google will turn those long documents into your next favorite podcast

Google Audio Overview
(Image credit: Google)

If you have a lot of reading to do for school or work but would rather listen to a podcast, Google's new AI-powered Audio Overview tool has you covered. As first demonstrated at Google I/O this year, Audio Overviews lets you convert documents, slides, and other text into an audio show where AI hosts discuss the topic. Google is pitching the feature as a way for people who learn better by listening than reading to digest complex information. The feature personalizes learning for you if you would rather hear a topic discussed than read reports. 

Audio Overviews are part of the NotebookLM note-taking app introduced earlier this year. The feature relies on Google's Gemini AI models to summarize and organize documents, enhancing them with audio AI. The most interesting bit is that it's not just an AI voice reading the same text summary; you'll hear synthetic personalities talking about the documents to each other. The virtual hosts explain the subject and the connections between different topics in the documents. They try to make studying and research easier or at least something you can enjoy while driving. The back-and-forth discussion even includes jokes and banter like you've commissioned a hyper-specific podcast episode just for you. You can hear an example below based on this Google blog post on NotebookLM. 

Google Audio Overview

(Image credit: Google)

Your AI Podcast Pals

NotebookLM includes a generate button within the app to make an Audio Overview from a notebook. Once the overview is made, you can download the file and listen to it whenever you want. The audio is built using just your uploaded files; however, there is no additional research, so it's hardly a comprehensive study guide. Plus, as with all AI-generated content, you have to watch out for hallucinations and wrong information.

At I/O, Google promised that there would be more advanced versions of Audio Overviews to come. That includes the possibility of real-time interaction, not just a passive listening experience. It would turn the audio from a podcast to more of a call-in radio show with an audience of one and hosts who only want to talk about a very specific set of information. And while Google is centering Audio Overviews on academic or other research and studying, it's very easy to imagine the same tech being used for hyper-focused (and conversational) news reports or perhaps even a way of getting all the updates on your friends and family from their social media posts. 

You might also like

Eric Hal Schwartz
Contributor

Eric Hal Schwartz is a freelance writer for TechRadar with more than 15 years of experience covering the intersection of the world and technology. For the last five years, he served as head writer for Voicebot.ai and was on the leading edge of reporting on generative AI and large language models. He's since become an expert on the products of generative AI models, such as OpenAI’s ChatGPT, Anthropic’s Claude, Google Gemini, and every other synthetic media tool. His experience runs the gamut of media, including print, digital, broadcast, and live events. Now, he's continuing to tell the stories people want and need to hear about the rapidly evolving AI space and its impact on their lives. Eric is based in New York City.

TOPICS