Summary
- NotebookLM’s Audio Overview feature, which creates podcast-style audio discussions from research, is now integrated directly into Google Gemini on web and mobile apps, making it more accessible for auditory learners.
- Audio Overview in Gemini is powered by the free-to-use Deep Research model, allowing all users to generate audio summaries, though non-paying users are limited to five Deep Research reports (and thus audio overviews) per month.
- In addition to Audio Overview, Gemini also gained a new feature called Canvas, an interactive workspace for real-time document editing and code prototyping with AI assistance.
Google’s Gemini-powered NotebookLM is a great learning tool for auditory learners who understand topics and themes better when heard rather than simply read. The tool, which is already easily accessible via notebooklm.google.com is now even easier to access, all thanks to it finally being directly integrated within Gemini on both the mobile apps and the web.
The development comes soon after Google announced that it was expanding access to several Gemini Advanced features for free users, including support for Gemini Flash Thinking, Deep Research, and Personalization.
Related
Gemini’s new history-crawling model is rolling out to all with Deep Research in tow
New features and expanded availability? Count us in
The new tool, aptly named Audio Overviews, functions similarly to its implementation on NotebookLM, albeit with a few modifications. For starters, Audio Overviews are (at least currently) only available via the Gemini Deep Research model. The model is free-to-use for all, which means you will be able to generate Audio Overviews for topics that you dig into without having a Gemini Advanced subscription.
It’s worth noting, though, that non-paying users can only use Deep Research for five detailed reports per month, which, in turn, also limits the number of Audio Overviews users can generate.
You can begin playing around with Gemini Audio Overviews today
To generate podcast-like spoken dialogue discussion for topics, head to Gemini and select the Deep Research model from the model selector. Type in your query and ‘Start research.’ This step should take a few minutes to complete. Once completed, you’ll be presented with a comprehensive overview of your research topic, complete with the option to pose follow-up questions.
You’ll also see an option to Export to Docs, as seen in the fourth slide below, though we’re more interested in the arrow adjacent to it. Tap/click the arrow, and you’ll be presented with the option to Generate an Audio Overview. Once generated, you can listen to the overview within Gemini, or download it for later.
Audio Overviews within Gemini are rolling out now to users globally, albeit only in English. The feature is available to me on the web, but as is often the case, support for the mobile app seems to be lagging behind.
Elsewhere, with the same ‘feature drop,’ Gemini today also gained Canvas, a tool that Google described as an “interactive space within Gemini designed to make creating, refining and sharing your work easy.” The tool, which can help with real-time document editing and code prototyping.
The tool offers feedback and suggests edits for your drafts, complete with editing tools to “adjust the tone, length or formatting” of your written content. Similarly, Canvas can also help users learn to code by bringing their ideas to life. “Canvas empowers developers to quickly create initial working versions of their projects and provides a space for students to quickly learn coding concepts,” wrote Google. Canvas for coding and real-time document editing is rolling out to all users in all languages supported by Gemini Apps.
