Google NotebookLM is getting a new feature that can turn your documents into engaging audio discussions like podcasts. The Mountain View-based tech giant on Wednesday announced the new feature called Audio Overview. This feature is available to all users who agree to try NotebookLM which is still available as an experimental tool. This feature is not a simple text-to-speech rendering, rather it uses AI to generate full conversations, including jokes. Notably, this tool was first introduced in India and other select regions in June.
Google NotebookLM gets audio overview feature
In a blog post, Google explained the new feature in detail and revealed that the audio overview has now been rolled out. Gadgets 360 staff members were able to identify 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 must first 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 is added, users need to click on the Notebook Guide icon below. This will pop up an interface where a summary of the document as well as suggested hints can be seen.
At the top right, there is a new section for audio overview. Tapping on Generate will begin the process of converting the content into an engaging audio discussion. The format consists of a male and a female AI host who discuss the topic.
In our testing, we found conversations to be very human-like, with AI hosts emphasizing relevant words, modulating voices and taking pauses for dramatic effect. Additionally, the AI hosts even interrupt each other to make it look like a real conversation. Interruptions are made either to further what was said or to make the information more relevant. The AI hosts also joke and joke. Once generated, the audio files can also be downloaded.
Additionally, the feature appears to be using the internet to find out more information about the topic, as we’ve seen the audio overviews go more in-depth than the source material at times. However, Google says, “It’s important to remember that these generated discussions are not a comprehensive or objective view of a topic, but merely a reflection of the sources you uploaded.”
The feature also has some limitations. Calling audio overviews an experimental feature, Google says it may take several minutes to generate an audio discussion. This feature currently only supports the English language, so users will not be able to generate audio in other languages. Furthermore, the tech giant highlighted that the AI host cannot be disrupted, and may contain errors.
