4 Sources
[1]
Google will let you make AI podcasts from Gemini's Deep Research
Emma Roth is a news writer who covers the streaming wars, consumer tech, crypto, social media, and much more. Previously, she was a writer and editor at MUO. Google's Gemini app now lets you generate Audio Overviews based on Deep Research. That means you can turn the in-depth reports generated by
[2]
Google Gemini Can Now Turn Almost Anything Into a Podcast
Summary Google Gemini introduces Audio Overviews, allowing users to create podcasts from uploaded documents. Audio Overviews utilize AI to generate realistic voices and engaging discussions on document content. Audio Overviews provide a convenient way to extract information from documents in a
[3]
Gemini app rolling out Audio Overviews to Android, iOS
As announced earlier this week, the Gemini app is getting the ability to generate Audio Overview podcasts, with Android and iOS users beginning to see this capability today. Audio Overviews have widely rolled out on the web for free Gemini and paid Advanced subscribers in English, with more
[4]
You Can Now Generate Podcast-Style 'Audio Overviews' Directly in Gemini AI
Last year, Google released a niche feature in its experimental NotebookLM product that turned out to be a sleeper hit. You could upload any document to NotebookLM, and it would use AI to generate a two-person conversational podcast out of it. These aren't meant to be uploaded online for viewership,
Share
Copy Link
Google's Gemini app now offers Audio Overviews, an AI-powered feature that transforms documents, presentations, and Deep Research reports into podcast-style conversations, enhancing user engagement with content.

Google has rolled out a new feature called Audio Overviews in its Gemini app, allowing users to transform various types of content into AI-generated podcast-style conversations. This innovative tool, previously available in Google's NotebookLM, is now accessible to both free and Advanced Gemini subscribers
1
2
.Audio Overviews utilize artificial intelligence to create engaging discussions between two AI-generated hosts based on the content of uploaded documents, presentations, or Deep Research reports. The feature aims to summarize material, draw connections between topics, and provide unique perspectives in a conversational format
3
4
.Users can generate Audio Overviews from various sources:
2
To create an Audio Overview, users can:
3
4
The generated podcasts typically range from 5 to 15 minutes in length, depending on the content volume. For instance, a 146-page camera manual produced a 15-minute podcast, while a single-page PDF resulted in a 5-minute discussion
2
.A particularly useful application of Audio Overviews is its integration with Gemini's Deep Research feature. Users can prompt Gemini to create a comprehensive report on any topic and then generate an Audio Overview based on that research. This allows for easy digestion of complex information without the need to read through lengthy reports
2
4
.Related Stories
While the feature is widely available on web browsers for both free and paid Gemini users, the mobile app experience has some limitations. The Gemini app lacks a built-in audio player, instead opening audio files in a browser tab. This allows for easy downloads but creates a somewhat disjointed user experience
3
.Currently, Audio Overviews are available in English, with support for more languages planned in the future. The feature is accessible on both Android and iOS devices, as well as through the Gemini website
3
.Audio Overviews present numerous possibilities for content consumption and learning:
1
2
4
As this technology continues to evolve, it could potentially reshape how we consume information, making it more accessible and engaging for a wider audience.
Summarized by
Navi
[2]
[3]
1
Science and Research

2
Policy and Regulation

3
Technology