Particle Launches Radar, an AI Search Engine for 130,000+ Podcasts

Particle Launches Radar, an AI Search Engine for 130,000+ Podcasts

Particle has launched Radar, a podcast search engine and API that transcribes audio, identifies speakers and topics, and makes spoken conversations searchable by people and AI agents. The company says Radar currently indexes more than 130,000 podcasts and adds about 20,000 new episodes each day.

The product grew out of a feature inside Particle’s AI newsreader, which surfaced notable podcast clips alongside related news stories. Particle eventually separated that capability from the consumer app and turned it into a standalone intelligence product as demand grew from businesses and AI developers.

Particle co-founder and CEO Sara Beykpour said hedge funds have been among the strongest early customers. “Hedge funds have been the highest-volume customers that are directly integrating with the API,” Beykpour told TechCrunch.

AI search companies and data resellers are also using the service. Exa, which provides search infrastructure for AI agents, is one of Radar’s partners.

Radar is designed to solve a limitation Particle sees in existing web search and agent infrastructure: most systems are built primarily around text. Podcast discussions can therefore remain difficult for agents to access unless the audio has already been transcribed and structured. “Our vision is really to have all new media intelligence and all audio intelligence in that API,” Beykpour said. “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.” She added: “Agents are generally blind to audio; they can’t see it unless something or someone has transcribed it.”

Radar covers the Apple Top 200 podcasts across 135 categories. Its transcripts include speaker identification along with metadata for people, companies, brands, products and subjects mentioned during each episode. That structure allows users to search beyond individual words. Radar can track when particular entities appear across podcasts and send notifications when specified people or topics are mentioned. Those alerts can be delivered through email, Slack or webhooks and can be configured around specific conditions. A user could, for example, monitor for a particular guest discussing a selected topic or restrict searches to higher-ranked podcasts.

Radar also extracts individual clips and attaches timestamps, allowing users to jump directly to relevant portions of an episode rather than listening to the full recording or relying only on a summary. “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 said.

Particle is layering additional data on top of the transcripts. Radar can track podcast topics, entities, listener reviews, ratings and advertising. A separate advertising search tool can identify episodes where a particular company ran ads and follow those appearances over time.

Other available data includes political bias analysis, podcast rankings, estimated audience size, sponsorship information and brand-suitability signals.

Although Radar has a web interface, Particle is positioning its API and MCP access as the core offering for companies and AI systems that want to incorporate podcast intelligence directly into their own products.

The service costs $29 per month for an individual seat. A business plan costs $399 per month and includes 20 seats, while API pricing is customized according to usage.

Particle plans to broaden Radar beyond podcasts in the future, with YouTube videos and news clips among the additional audio sources it intends to support. The shift gives Particle a different role from its original newsreader product. Rather than primarily presenting AI-organized news to consumers, the company is now building infrastructure that lets other systems search and analyze information that was previously locked inside audio.

This analysis is based on reporting from TechCrunch.

Image courtesy of Particle/Radar.

This article was generated with AI assistance and reviewed for accuracy and quality.

Updated Aug 26, 2026

About this article: This article was generated with AI assistance and reviewed by our editorial team to ensure it follows our editorial standards for accuracy and independence. We maintain strict fact-checking protocols and cite all sources.

Word count: 634Reading time: 0 minutes

📧 Stay Updated

Get the latest AI news delivered to your inbox every morning.

AI News Daily

Breaking Intelligence • Since 2023

Join hundreds of thousands of AI professionals who start their day with our curated newsletter. Get breaking news, expert analysis, and exclusive insights.

Stay Ahead of AI

Get the latest AI breakthroughs, tools, and insights delivered to your inbox every week.

Free forever Unsubscribe anytime No spam guarantee

Go Premium

Unlock unlimited AI tools and an ad-free reading experience designed for AI professionals.

• Ad-free experience• Premium AI tools
Start Free Trial

14-day free trial • Cancel anytime
Plus $9/mo • Pro $90/yr (2 months free)

Follow Our Community

ChatAI

Breaking Intelligence

Your daily briefing on what matters in AI. Trusted by developers, researchers, executives, and AI enthusiasts worldwide.

© 2026 ChatAI. All rights reserved.