Particle’s AI news app listens to podcasts for interesting clips so you don’t have to

An AI news app called Particle, from former Twitter engineers, can now follow breaking news on podcasts as well as news published on the web.

Prior to its recent Android release, Particle introduced a feature called Podcast Clips, which finds the most interesting and relevant moments across many different podcast types, and then embeds those clips alongside related news stories in its feed.

So instead of listening to a lengthy podcast just to catch 45 seconds of interesting commentary, you can play the clip while you read the news on Particle. You also have the option to read the text of the passage instead, with words highlighted as they are spoken.

“We basically did this for any news story — if there was a podcast talking about it, or relevant at all, we had all those clips,” Sarah Beykpour, CEO of Particle and formerly Twitter’s senior director of product management, told TechCrunch. “It’s a really great way, when you’re reading a story or learning about it, to see what people are saying about it? What’s the commentary?”

The addition recognizes a shift in the news ecosystem that has been underway for years. Not only are more people getting their news from podcasts and trusting them as reliable sources, but the medium has also become a destination for breaking news and major announcements from public figures.

Tech CEOs, in particular, are now looking for approachable podcast hosts to broadcast their talking points rather than trying to work with traditional media, as Bloomberg reported in 2024.

This makes paying attention to podcasts even more important if you want to keep up with the news.

Beykpour says Particle uses embedding models to understand when podcasts link to a particular news story. She explains that these models are provided by the same companies that offer LLM models, but they are not generative AI techniques.

“We use vector embeddings to understand that these different parts of the podcast are connected to these different stories,” Beykpour says. “One podcast might cover 10 or 20 stories, so we use AI to understand that. We also use AI to do some reasoning around the storytelling, and understand when a segment starts and ends.”

The company leverages ElevenLabs’ copy technology. However, some of the techniques that pinpoint exactly where sound clips are part of Particle’s secret sauce.

The idea of ​​leveraging podcasts to better understand commentary on news is also something newsrooms are taking a closer look at these days. As Nieman Lab reported this month, The New York Times used a custom AI tool that uses master’s degree holders to write and summarize new episodes for dozens of right-wing and more conservative podcasts to better understand what influencers on that side of the story are saying about the news.

Particle’s Podcast Clips feature isn’t just about news stories. Since the app already understands different entities — such as people, places, or things — you can go to the page of a notable figure, such as OpenAI CEO Sam Altman, to see all of their podcast appearances arranged as a summary.

Particle has been busy building other features as well. The company made its first attempt at monetization with Particle+, an optional $2.99 ​​per month (or $29.99 per year) subscription that gives you access to premium features. These include the ability to use natural language to summarize news in the style you prefer; Choose from different voices when using custom audio streaming; “Listen to the news”; Unlimited number of crosswords; Support private questions with its AI-powered chatbot; And more.

The Android version also brings some other notable changes. The browsing tab now includes recent stories, such as the 2026 Winter Olympics, as well as typical sections such as politics, technology, or entertainment. Additionally, when you click on an entity, you’ll see a new page containing the definition, stories, articles, related entities, and related topics.

Particle doesn’t share data about user activity or conversion rates, but Beykpour noted the app’s international audience, pre-Android. On a weekly basis, 55% of Particle users are from outside the US, with India (15%) being its largest market after the US.