Particle, the AI newsreader startup founded by former Twitter engineers, has introduced Radar, a podcast search engine that transcribes and understands audio content. The tool allows users to search for key quotes and highlights from podcasts, making the content discoverable and usable by AI agents. The service is already attracting interest from hedge funds and other businesses seeking data that their agents can’t access directly. 'Hedge funds have been the highest-volume customers that are directly integrating with the API,' said Particle co-founder and CEO Sara Beykpour.
Radar transcribes more than 130,000 podcasts, making it the largest transcribed podcast service in existence. This includes all the Apple Top 200 podcasts across its 135 verticals, with 20,000 episodes added to Radar’s index daily. The transcriptions include speaker labels and rich metadata, as Radar understands the entities — people, companies, brands, products, and topics — being discussed. It can also track mentions of these entities across podcasts and send alerts when they come up, either in real time or as a daily or weekly digest.
The idea for Radar stemmed from one of Particle’s most beloved features in its news-reading app, which sourced interesting podcast clips to include alongside related news stories. The company realized the product’s value but also that it was somewhat trapped in the news reader. As the movement around AI agents gained momentum, Particle decided to pivot and focus on building an API for its podcast intelligence product.
Source: techcrunch
