Particle, the AI newsreader startup founded by former Twitter engineers, has launched Radar, a podcast search engine that transcribes and semantically indexes spoken content, making it discoverable and accessible to AI agents via API. According to co-founder and CEO Sara Beykpour, the idea grew out of a feature in Particle‘s news-reading app that surfaced relevant podcast clips alongside stories. The team realized the underlying intelligence was more valuable as a standalone product, especially as AI agents increasingly need to access audio data, which they are typically blind to.

Radar currently transcribes more than 130,000 podcasts — the company says it is the largest transcribed podcast service — including all Apple Top 200 podcasts across 135 verticals, with 20,000 new episodes added daily. The transcriptions include speaker labels, entity recognition (people, companies, brands, products, topics), and rich metadata. Users can search across this corpus, set up alerts for mentions of specific entities, filter by guests and topics, and receive notifications via email, Slack, or webhook. Radar also extracts notable self-contained clips with timestamps, enabling quick listening or reading without going through the full episode.

Beyond search, Radar tracks topics, mentions, listener ratings, ads, and more. It includes a dedicated podcast ads search engine that finds every episode where a given company advertises and tracks trends of that advertising over time. Additional tools offer political bias analysis, chart rankings, audience size estimates, sponsorship data, and brand suitability.

The product is available through a web interface, but the core offering is an API and an MCP (Model Context Protocol) server, allowing AI agents and businesses to programmatically access the same intelligence. Pricing is $29 per month per seat, with a $399 per month business plan covering 20 seats; API usage has custom pricing. Beykpour noted that hedge funds have been the highest-volume customers directly integrating with the API, while AI search platforms and data resellers are also paying customers. Exa, a search API provider for AI agents, is a partner.

Particle plans to expand Radar beyond podcasts to other audio forms such as YouTube videos and news clips in the future. The article notes that while journalists and researchers could use the tools, the business focus is on the API layer for AI agents and data-driven clients.