Particle, the AI newsreader startup founded by former Twitter engineers, is pivoting to a new market: making podcasts searchable and usable by AI agents. On Wednesday, the company launched Radar, a podcast search engine that transcribes and semantically indexes over 130,000 shows, allowing users to search for specific quotes, topics, and entity mentions. The product has already attracted interest from hedge funds seeking data that their AI agents cannot otherwise access, according to co-founder and CEO Sara Beykpour.
“Hedge funds have been the highest-volume customers that are directly integrating with the API,” Beykpour told TechCrunch. The tool is also being used by AI search platforms and data resellers, with Exa, a search API provider for AI agents, among Radar’s partners.
Also read: Bill Gates Proposes 'Robot Tax' and 'Human Reserved' Jobs to Counter AI Job Displacement
From newsreader feature to standalone product
Radar originated from a feature in Particle’s news-reading app that sourced podcast clips to accompany related news stories. The team recognized the value of the technology but realized it was limited within the confines of a newsreader. As interest in AI agents grew, the company decided to pivot and build an API around its podcast intelligence.
“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.”
Also read: Z.ai confirms it’s the lab behind Ox Alpha, the open-weight model topping AI leaderboards
What Radar offers
Radar indexes all Apple Top 200 podcasts across 135 verticals, adding 20,000 episodes daily. The transcriptions include speaker labels and rich metadata, with the system understanding entities such as people, companies, brands, and products. Users can track mentions of these entities and receive alerts via email, Slack, or webhook, with filters for specific guests or topics.
The service also extracts self-contained clips with timestamps, allowing users to listen to or read key moments without wading through full episodes. “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.
Additional features include a dedicated podcast ads search engine that tracks where companies advertise and how that trends over time, as well as tools for political bias analysis, chart rankings, audience size estimates, sponsorship data, and brand suitability.
Implications for AI agents and the data economy
The launch highlights a growing gap in the AI ecosystem: while agents can crawl and understand text-based web content, audio remains largely inaccessible. Radar aims to fill that void by providing a transcription and understanding layer that agents can query via API. This has particular appeal for hedge funds and other data-driven businesses that rely on timely information from podcasts, which often contain insights not yet reflected in written articles.
For journalists and researchers, Radar offers a way to quickly find expert commentary or original quotes across thousands of shows, potentially saving hours of manual listening. The API also opens possibilities for AI search platforms to include audio content in their results, expanding the types of information available to users.
Radar is available through a web interface, but its core product is the API and MCP (Model Context Protocol) integration, enabling AI agents to tap into the intelligence programmatically. Pricing starts at $29 per month per seat, with a $399-per-month business plan for 20 seats. API access is custom-priced based on needs.
Looking ahead, Particle plans to expand Radar beyond podcasts to other audio formats, including YouTube videos and news clips. As AI agents become more prevalent, the demand for audio intelligence is likely to grow, and Radar appears positioned to capitalize on that trend.
Disclaimer: This article is for informational purposes only and does not constitute financial advice. The cryptocurrency and AI markets are volatile and uncertain; readers should conduct their own research before making any investment decisions.
Be the first to comment