Radar turns podcasts into searchable, AI-readable data
A startup called Particle has built a search engine that transcribes more than 130,000 podcasts and makes the spoken word inside them usable by AI agents. Hedge funds are already paying for it.
Key points
- Particle, founded by former Twitter engineers, launched Radar, a podcast search engine, on Wednesday.
- Radar transcribes more than 130,000 podcasts daily, adding 20,000 new episodes to its index every day.
- Hedge funds are among the highest-volume paying customers, integrating Radar's API, a software connection that lets other programs pull in its data, directly into their research tools.
- Personal plans start at $29 a month; business plans cost $399 a month for 20 seats.
- Particle plans to expand Radar beyond podcasts to YouTube videos and news clips.
Most of the conversation happening on the internet is not written down. It is spoken: on podcasts, in interviews, across hundreds of thousands of audio episodes published every week. Until now, that content was largely invisible to AI.
Particle, an AI startup founded by engineers who previously worked at Twitter, wants to fix that. On Wednesday the company launched Radar, a service that listens to podcasts, turns them into text, understands who and what is being discussed, and makes all of it searchable.
What does Radar actually do?
Radar transcribes audio and then goes a step further: it identifies the people, companies, products and topics mentioned, so you can search for a name and find every podcast moment that name appears in.
Think of it like a Google News alert, but for spoken audio. A user can set up Radar to send a notification by email or workplace messaging app Slack whenever a specific company or person is mentioned on a podcast, with a clip and a timestamp attached. The clips are self-contained, so you can read or listen without sitting through a full episode.
Radar covers all 200 of Apple's top-ranked podcasts across 135 subject categories. That makes it, by the company's own count, the largest transcribed podcast service currently available.
Who is paying for this?
Hedge funds are the biggest customers right now. That may sound surprising, but it makes sense: financial analysts spend enormous effort monitoring what executives, economists and market commentators say publicly, and podcasts have become a major venue for those conversations.
"Agents are generally blind to audio; they can't see it unless something or someone has transcribed it," Particle co-founder and CEO Sara Beykpour told TechCrunch. AI agents, meaning software programs that carry out research or tasks automatically, crawl websites for text. They cannot listen. Radar gives them ears.
AI search platform Exa is already listed as a Radar partner. Journalists, researchers and data resellers are also among the paying users.
| Plan | Price | What you get |
|---|---|---|
| Personal | $29/month per seat | Web search, alerts, clip extraction |
| Business | $399/month | 20 seats, full feature set |
| API | Custom pricing | Programmatic access for developers and businesses |
The API, a technical connection that lets other software pull Radar's data automatically, is described by Particle as the core product. An MCP, a newer standard that makes it easier for AI agents to call up outside data sources, is also available.
What does this mean for ordinary listeners?
Nothing changes about how podcasts sound or where you find them. Radar works in the background, reading content that is already public.
For professionals who track brands, public figures or market trends, the practical upside is real: less time listening to hours of audio, more targeted alerts when the moments that matter actually happen.
Particle says it plans to extend Radar beyond podcasts to YouTube videos and broadcast news clips, widening the pool of spoken content that AI tools can finally read.
Common questions
Do podcast creators need to opt in?
Radar transcribes publicly available podcast audio, in the same way a search engine indexes public websites. No opt-in from creators is required under current practice.
Is my private audio at risk?
Radar indexes public podcast feeds only. Private or paywalled episodes that are not in a public RSS feed, the standard distribution format podcasts use, are not included.
Can I use Radar without a technical background?
Yes. The web interface lets anyone search podcasts, set up alerts and read extracted clips without writing any code. The API and developer tools are aimed at businesses building their own software on top.
