Founded by former Twitter engineers, Particle is shifting its strategy from a news-reading app to a robust intelligence provider. Radar functions as a specialized layer for AI agents that are typically blind to audio content. The service processes the Apple Top 200 podcasts across 135 verticals, adding 20,000 episodes to its index every day. Beyond simple transcription, the system identifies specific entities—including companies, brands, and products—and tracks their mentions across the entire catalog.
Particle pivots to audio intelligence with Radar podcast search engine
Hedge funds are lining up for Radar, a new search engine from AI startup Particle that indexes and transcribes over 130,000 podcasts daily. By converting spoken content into searchable data, the platform provides AI agents with the missing context they need to navigate the previously inaccessible world of audio media.
CEO Sara Beykpour confirms that high-volume demand is currently coming from financial firms and data resellers who rely on the platform’s API to feed their autonomous agents. Users can configure automated alerts via Slack, email, or webhooks to monitor specific guests or topics in real time. The platform also features a dedicated search engine for podcast advertising, allowing brands to track sponsorship trends and competitor placements. While the web interface offers a consumer-facing dashboard, the core business model centers on API access and Model Context Protocol (MCP) integrations. Monthly pricing starts at $29 for individuals, with enterprise tiers and custom API agreements available to support large-scale data ingestion.
Comments (0)
No comments yet. Be the first!