Particle launches Radar podcast search

Particle launches Radar podcast search

Particle, the AI newsreader startup founded by former Twitter engineers, has shifted its focus to indexing spoken conversations in podcasts. On Wednesday, the company introduced Radar, a search engine that transcribes podcast audio and interprets its meaning, enabling extraction of key quotes and highlights.

The move follows interest from hedge funds, which Particle says are the highest-volume customers directly integrating with the API. “Hedge funds have been the highest-volume customers that are directly integrating with the API,” CEO Sara Beykpour told TechCrunch. Journalists, researchers, AI search platforms and data resellers also use the tool; the search-API provider Exa is among Radar’s partners.

Radar grew out of a feature in Particle’s news-reading app that sourced podcast clips to accompany news stories. Realising the broader value, the team pivoted to an API-centric product. “We are providing that layer with audio,” Beykpour explained. “Agents are generally blind to audio; they can’t see it unless something or someone has transcribed it.”

The service now contains more than 130,000 transcribed podcasts, making it the largest such database. It includes all Apple Top 200 podcasts across 135 verticals, and adds 20,000 episodes to its index each day. Transcriptions feature speaker labels, rich metadata, and entity recognition for people, companies, brands, products and topics.

Users receive alerts when entities appear, delivered via email, Slack or webhook. Filters let clients specify guests, topics or podcast tiers. Radar also extracts self-contained clips with timestamps, allowing listeners to hear or read concise segments. “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,” Beykpour said.

Beyond clips, Radar tracks topics, episode ratings, reviews, ads and more. A dedicated ads search engine finds every episode where a company advertises, tracking trends over time. Additional tools offer political bias analysis, chart rankings, audience size estimates, sponsorship data and brand suitability.

While the web interface provides access, the core product is the API and MCP, enabling AI agents and businesses to tap the intelligence programmatically. Pricing is $29 per month per seat, with a $399-per-month plan for 20 seats. API users receive custom pricing based on needs.

Future plans include extending the service to other audio formats such as YouTube videos and news clips.

Pricing

For comparable metrics, see our stats. The upcoming releases can be checked in the fixtures section, and the team’s lineup is listed under squad.