Can AI-generated podcasts boost science engagement?

“My brain starts to die when I try to read a journal article,” says Jessica Sacher, a microbiologist at Stanford University in California. Papers are written to be technically comprehensive rather than understandable, she says. “I just want someone to tell me what the gist is.”

Now, artificial intelligence (AI) chatbots can help to turn difficult concepts into clear, engaging podcasts, providing a simpler method for keeping up with the literature. Now, Sacher regularly absorbs the latest research by tuning in to AI-made conversations.

A flurry of AI podcasts has emerged (see ‘AI podcast tools’). Some tools require minimal input from the user. Others come equipped with customizable features, such as the option to change the voices or languages of the ‘hosts’.

Learning on the go

AI podcast tools can boost engagement in several ways. Benjamin Gooddy, a neuroscience PhD student at King’s College London, uses them to digest his database of papers that are relevant to his work.

“I can chuck in 50 papers at once, and it can spit out pretty user-friendly audio,” he says. “I actually use it as a podcast to listen to on the tube into work.”

The podcasts can also help with exam revision. Mmesoma Francis, a student at Kyiv Medical University, says that the tools helped her to cram 60 pages of material the day before one of her classes.

“I just put the PDF in, and it made this podcast that was 17 minutes long,” she says. “I use it now on an almost daily basis because it helps give an overview of the topic, even if I plan to do in-depth studying after.”

In a study¹ posted on the arXiv preprint server earlier this year, philosophy students who listened to AI podcasts performed better on tests than did those who only read textbooks.

Other researchers argue that the podcasts are better suited to public outreach than to digesting the literature. Pedro Beltrao, a geneticist at the Swiss Federal Institute of Technology in Zürich, says that robo-podcasters tend to explain basic concepts using multiple analogies at the expense of diving into details, which can make the tool less useful for specialists who want to keep up with studies in their field. Sacher works on phage therapy and says she wishes she could skip past all of the openings that introduce phages as viruses that infect bacteria.

Gooddy says that AI podcasts could help researchers to persuade news outlets to cover studies that might “have gone under the radar because perhaps they were almost too technical or just very dry, but the actual research findings might be quite exciting”.

Compared with standard podcasts, which are resource-intensive to make and tend to focus on buzzworthy studies that have the best chance of drawing large audiences, AI podcasts allow scientists to promote less eye-catching papers at a much lower cost.

Early-stage limitations

The tools are promising, but still in their early iterations. Beltrao finds that podcasts that cover multiple papers tend to discuss them one at a time rather than integrating them. “The hope would be that if you provided a few papers, maybe it would start to make connections,” he says.

Gooddy, however, has had a different experience, and says integration can work. “It linked together some papers that I hadn’t necessarily linked myself.” One podcast about several neuroscience papers highlighted a brain region he had overlooked, prompting him to shift his focus.

2024 Research Leaders

Condensing a large study into a short discussion means some sections will get skipped and others overemphasized. “It does seem to sometimes get fixated on a particular thing that you might not be as interested in,” Gooddy says.

Beltrao also finds that the podcasts sometimes make blunders. He used it to summarize a PhD thesis he’d read. “It made a factual mistake,” he says. Beltrao advises researchers to fact-check the podcasts before sharing them publicly.

As the tools evolve and become more reliable and accessible, they will “enable everyone to be more up to date on the literature”, Sacher predicts. Francis plans to use them as a study tool when covering new topics. And whenever Beltrao’s team puts out a new paper, he aims to share AI-made podcasts on social media to get the word out.

Nature Index’s news and supplement content is editorially independent of its publisher, Springer Nature. For more information about Nature Index, see the homepage.