Particle just made billions of spoken words searchable for machines
Signals InboxAugust 26, 2026AI Knowledge & Search
The launch matters because it changes what users can actually do now. Podcasts just became machine-searchable.
The web is searchable. Podcasts should be too.
— sara beykpour (@pandemona) August 26, 2026
Introducing Radar by @particlepro_.
Radar lets you search and spot trends in over 130,000 actively transcribed podcasts, with ~20k new episodes added daily.
Millions of hours, billions of lines: all fully searchable, entity… pic.twitter.com/3VzrGcdjay
Q1What did Particle launch?
According to the official source, particle introduced Radar, a search and trend tool covering more than 130,000 actively transcribed podcasts, with roughly 20,000 new episodes added each day.
Q2Why is podcast search still hard?
Podcast information lives inside audio rather than indexed text pages. Transcribing and structuring millions of hours turns a largely opaque medium into something that models and researchers can query directly.
Q3What can this unlock?
Users can search mentions, entities, narratives, and emerging topics across shows instead of listening episode by episode. That makes podcasts more useful as a real-time research dataset.
Q4What is the moat?
The model layer is increasingly commoditized. The defensible asset is the continuously updated corpus, entity resolution, metadata, and ranking needed to make billions of spoken words genuinely searchable.