Radar Makes Podcasts Searchable β and Ready for AI Agents
Particle, the AI-powered newsreader startup founded by former Twitter engineers, is shifting its focus to a potentially more lucrative opportunity: indexing the spoken conversations buried in podcasts and making them discoverable. As of 2026, the company has launched Radar, a podcast search engine that not only transcribes audio but also understands its meaning, enabling it to extract key quotes and highlights.
The move comes as AI agents increasingly rely on structured data from diverse sources. Radar aims to fill a critical gap: the vast, unstructured audio content that remains invisible to traditional text-based search and AI systems.
Business Appeal: Hedge Funds and Beyond
Radar has already attracted significant interest from hedge funds seeking data that their AI agents cannot currently access, according to Particle co-founder and CEO Sara Beykpour. "Hedge funds have been the highest-volume customers that are directly integrating with the API," Beykpour told TechCrunch. While journalists and researchers could also benefit from the tools, other top-paying customers include AI search platforms and data resellers. Notably, Exa, a search API provider for AI agents, is among Radar's partners.
From News Feature to Standalone API
The idea for Radar grew out of a popular feature in Particle's news-reading app, which used an API to source interesting podcast clips and include them alongside related news stories. The team recognized the feature's value but realized it was somewhat trapped within the news reader. As the momentum around AI agents accelerated, Particle decided to pivot and build a dedicated API for its podcast intelligence technology.
Technical Capabilities and Deployment
Radar combines automatic speech recognition with advanced natural language understanding to deliver:
- Full transcriptions of podcast episodes
- Semantic search across spoken content
- Extraction of quotable highlights and key topics
- API access for integration into AI agent workflows
With 2026 seeing a surge in agent-based applications across finance, research, and media, Radar positions itself as a critical infrastructure layer for unlocking the insights hidden in the world's rapidly growing podcast ecosystem.
via TechCrunch AI