Google NotebookLM Gets Audio Overviews Feature That Turns Documents into Audio Discussions

Google NotebookLM is receiving a new feature that can turn your documents into engaging podcast-like audio discussions. The Mountain View-based tech giant announced the new feature dubbed Audio Overviews on Wednesday. The feature is available to all users who consent to try out NotebookLM which is still available as an experimental tool. The feature is not a simple text-to-speech rendering, but it uses AI to generate a full-fledged conversation, including jokes. Notably, the tool was first introduced in India and other select regions in June.

Google NotebookLM Gets Audio Overviews Feature

In a blog post, Google detailed the new feature and highlighted that Audio Overviews has now been rolled out. Gadgets 360 staff members were able to spot the feature, and it should be available to anyone with access to the AI-powered note-taking tool.

The feature is easy to use. The user first needs to add a source, which can be a PDF, TXT, or markdown file as well as simple text pasted directly into the notebook platform. Once the source has been added, users will need to click the Notebook guide icon placed at the bottom. It will pop up an interface where the summary of the document as well as suggested prompts can be seen.

At the top right, there is a new section for Audio Overviews. Tapping on Generate will start the process of turning the content into an engaging audio discussion. The format includes a male and a female AI host who discuss the topic.

In our testing, we found that the conversation is very human-like, with the AI hosts emphasising relevant words, modulating voices, and taking pauses for a dramatic effect. Additionally, the AI hosts also interrupt each other to make it appear like a real conversation. The interruptions are done to either build on top of what was said or to contextualise the information further. The AI hosts also joke and banter. Once generated, the audio files can also be downloaded.

Further, it appears that the feature uses the internet to find more information about the topic, as we spotted the Audio Overview containing greater depth than the source material, at times. However, Google states, “It’s important to remember that these generated discussions are not a comprehensive or objective view of a topic, but simply a reflection of the sources that you’ve uploaded.”

There are some limitations to the feature as well. Calling Audio Overviews an experimental feature, Google says that it can take several minutes to generate a single audio discussion. The feature currently only supports the English language, so users will not be able to generate audio in other languages. Further, the tech giant highlighted that the AI hosts cannot be interrupted, and there might be inaccuracies.