Affiliate links on Android Authority may earn us a commission. Learn more.
Gemini could soon let you turn PDFs into podcasts (APK teardown)
- NotebookLM’s Audio Overviews could soon be coming to Gemini on your phone.
- Audio Overviews will generate spoken “podcasts” where hosts discuss the information in your documents.
- Gemini could start suggesting this option when you submit a document as input.
If you feel like AI is constantly being oversold, you’re not alone, and while it’s easy to appreciate stuff like the output you see people share from AI image generators, a lot of us are still looking for the AI tool that’s really going to transform our lives. Google’s introduced tons of AI tools over the course of the past year, but one of the most powerful — and one that more people could stand to learn about — is NotebookLM, a tool for summarizing sources and organizing notes. Now one of NotebookLM’s most interesting features could be getting ready to come to Gemini on Android.
An APK teardown helps predict features that may arrive on a service in the future based on work-in-progress code. However, it is possible that such predicted features may not make it to a public release.
Back in September, Google upgraded NotebookLM with Audio Overviews, a feature that scanned through your notes and rather than presenting you with a written summary, generated a podcast where two virtual hosts would discuss the topic in a casual, natural-sounding manner. That was very cool on its own, and now we think we’ve spotted work towards bringing this same functionality to Gemini on your phone.
We’re looking at version 15.48.33.sa.arm64 beta of the Google app today, and upon cracking it open we discover the presence of some new text strings:
<string name="assistant_zero_state_suggestions_create_podcast_prompt_query">Generate audio overview</string>
<string name="assistant_zero_state_suggestions_create_podcast_snippet_highlight">Generate audio</string>
<string name="assistant_zero_state_suggestions_create_podcast_snippet_simplified">overview</string>As if “create_podcast” weren’t suggestive enough, we even see Audio Overviews get a direct reference here. So how exactly would Google bring something like this to Gemini and how might it end up working?
Well, while we’re not able to get the app to start synthesizing podcasts from our notes just yet, we did manage to get this sort of half-working in the app, at least offering a preview of how these interactions could go.
When this is active, Gemini should start suggesting the Audio Overview option when you submit an appropriate document as your input. Upon choosing that, Gemini will start crunching the information contained within and… well, that’s about as far as we get right now. In the absence of the rest of this Audio Overview functionality being implemented, Gemini seems to just fall back to a text-based summary.
Still, this is very exciting to think about seeing completed, and having easy access to a tool capable of turning dry, boring notes into something that’s actually engaging to listen to. You should even be able to download the podcast to your device if you’re expecting to be with dealing with limited connectivity — this sounds perfect for catching up on stuff while traveling. Right now we don’t have a great sense for when Google might finish up its work here, but we’ll be keeping an eye out for further developments.