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

Google NotebookLM is receiving a brand new characteristic that may flip your paperwork into partaking podcast-like audio discussions. The Mountain View-based tech large introduced the brand new characteristic dubbed Audio Overviews on Wednesday. The characteristic is offered to all customers who consent to check out NotebookLM which remains to be accessible as an experimental device. The characteristic will not be a easy text-to-speech rendering, nevertheless it makes use of AI to generate a full-fledged dialog, together with jokes. Notably, the device was first launched in India and different choose areas in June.

Google NotebookLM Gets Audio Overviews Feature

In a weblog post, Google detailed the brand new characteristic and highlighted that Audio Overviews has now been rolled out. Gadgets 360 employees members had been capable of spot the characteristic, and it ought to be accessible to anybody with entry to the AI-powered note-taking device.

The characteristic is simple to make use of. The person first wants so as to add a supply, which could be a PDF, TXT, or markdown file in addition to easy textual content pasted instantly into the pocket book platform. Once the supply has been added, customers might want to click on the Notebook information icon positioned on the backside. It will pop up an interface the place the abstract of the doc in addition to steered prompts may be seen.

At the highest proper, there’s a new part for Audio Overviews. Tapping on Generate will begin the method of turning the content material into an interesting audio dialogue. The format features a male and a feminine AI host who talk about the subject.

In our testing, we discovered that the dialog may be very human-like, with the AI hosts emphasising related phrases, modulating voices, and taking pauses for a dramatic impact. Additionally, the AI hosts additionally interrupt one another to make it seem like an actual dialog. The interruptions are executed to both construct on high of what was stated or to contextualise the knowledge additional. The AI hosts additionally joke and banter. Once generated, the audio information will also be downloaded.

Further, it seems that the characteristic makes use of the web to search out extra details about the subject, as we noticed the Audio Overview containing higher depth than the supply materials, at occasions. However, Google states, “It’s essential to do not forget that these generated discussions are usually not a complete or goal view of a subject, however merely a mirrored image of the sources that you have uploaded.”

There are some limitations to the characteristic as nicely. Calling Audio Overviews an experimental characteristic, Google says that it could take a number of minutes to generate a single audio dialogue. The characteristic presently solely helps the English language, so customers won’t be able to generate audio in different languages. Further, the tech large highlighted that the AI hosts can’t be interrupted, and there is perhaps inaccuracies.