Particle, the AI newsreader startup founded by former Twitter engineers, is now betting on a more lucrative opportunity: making the conversations buried in podcasts searchable. On Wednesday, the company launched Radar, a podcast search engine that doesn’t just transcribe audio but also comprehends its meaning, allowing it to surface key quotes and highlights. The business potential is significant—hedge funds have already shown interest in accessing data their agents can’t otherwise see, says Particle co-founder and CEO Sara Beykpour. While journalists and researchers could also benefit, other high-paying clients include AI search platforms and data resellers. (For example, Exa, the search API provider for AI agents, is among Radar’s partners.)

The concept grew out of one of the most popular features in Particle’s news-reading app. The app had used an API to pull in interesting podcast clips, which it then paired with related news stories in the feed. The team recognized the value of this feature, but also saw that it was somewhat confined within the news reader. As the momentum around AI agents picked up, the company decided to pivot and build an API around its podcast intelligence product.

“Our vision is really to have all new media intelligence and all audio intelligence in that API. One of the reasons why it’s an interesting space is that most API agents and services crawl the web and they’re focused on text. We are providing that layer with audio,” Beykpour said. “Agents are generally blind to audio; they can’t see it unless something or someone has transcribed it.”

With Radar, the company has transcribed more than 130,000 podcasts, making it the largest transcribed podcast service available. This includes all the Apple Top 200 podcasts across 135 verticals, with 20,000 episodes added to Radar’s index each day. The transcriptions come with speaker labels and rich metadata, as Radar understands the entities being discussed—people, companies, brands, products, and topics.

Radar also tracks mentions of these entities across podcasts and sends alerts whenever they come up, either in real time or as a daily or weekly digest. Alerts can be delivered via email, Slack, or webhook, and can be customized with filters—for instance, users can set Radar to only notify them when certain guests appear and discuss a specific topic. Search can also be narrowed in other ways, such as limiting results to top podcasts only.

The tool can extract relevant, self-contained clips with timestamps, allowing users to both listen to and read the comments made. “We’ve pre-chosen notable clips, so if you can’t listen to the whole podcast and you don’t want to read a summary, this is the best way to just get an idea of what’s happening in that podcast,” Beykpour noted. Radar can also track topics mentioned, who or what was discussed and when, listener ratings and reviews, the episode’s ads, and more. There’s even a dedicated podcast ads search engine that can find every episode where a given company advertises and track trends over time. This feature adds another revenue stream, alongside tools offering political bias analysis, chart rankings data, audience size estimates, sponsorship information, and brand suitability.

While all of this is accessible through Radar’s web interface, the core product is its API and MCP, which lets AI agents and other businesses tap into the same intelligence programmatically. Radar is priced at $29 per month per seat, with a $399-per-month plan for businesses that includes 20 seats. API users get custom pricing based on their needs. Looking ahead, Radar plans to expand beyond podcasts to support other forms of audio, such as YouTube videos and news clips.