Particle's podcast search engine and intelligence platform — it transcribes and indexes 130,000+ shows so their spoken content becomes searchable by people and AI agents.
Last verified · 2026-08-27 · by Moe Ameen
Radar is a podcast search engine and intelligence platform from Particle, the AI news startup founded by former Twitter engineers and led by co-founder and CEO Sara Beykpour. Announced August 26, 2026, it transcribes podcast audio at scale and turns it into structured, searchable data — the pitch being that AI agents and search tools are mostly blind to audio unless someone transcribes it first, and Radar closes that gap through an API and an MCP (Model Context Protocol) endpoint.
Particle says Radar has transcribed more than 130,000 podcasts and adds roughly 20,000 episodes a day, covering the Apple Top 200 across 135 verticals. On top of the raw transcripts it layers speaker labels and metadata that identify entities — people, companies, brands, topics — and it extracts key quotes, highlights, and self-contained clips with timestamps. You can search across all of it, track when an entity gets mentioned, and get customizable alerts by email, Slack, or webhook when a name, topic, or show you follow comes up.
The heaviest users so far are not creators. Particle has said hedge funds are its highest-volume API customers, mining spoken conversations for signals their agents otherwise can't see, alongside AI search platforms, data resellers, journalists, and researchers. Radar also runs a dedicated podcast-ads search engine and surfaces sponsorship data, listener ratings, and brand-suitability signals, with plans to expand beyond podcasts into YouTube videos and news clips.
For a creator, the honest framing is that Radar is a research and monitoring layer, not a content tool. It finds and structures what was said on other people's shows; it writes no posts, edits no video, and publishes nothing. Its value sits at the very top of the funnel — spotting the quote, the trend, or the moment worth making content about.
Radar is a discovery instrument. It tells you what was said on the shows your audience actually listens to — the quotable line from a founder interview, the topic spiking across your niche this week, the competitor who just got name-checked on a Top 200 podcast. That is the hardest part of the top of the funnel: knowing what's worth making content about. What Radar hands you is a timestamped quote or a trend signal, not a post. [Kompozy](/) is the engine that turns that signal into a week of finished, published content.
Take a quote or clip Radar surfaced and drop it into Kompozy's Quick Ingest as your source. One input fans out into up to 18 on-brand formats: a [Persona Short](/glossary/persona-shorts) with an avatar reacting to the quote, a [Quote Graphic](/) built server-side, a brand-exact [carousel via HyperFrames](/glossary/hyperframes) unpacking the trend, native Text Posts and an X thread, plus a [blog article](/) and a newsletter — every output held to one [Persona Brief](/glossary/persona-brief) so your take reads as one brand, not twelve prompt runs. Then [Autopilot](/glossary/autopilot) reframes each asset per platform and schedules it across the eight social platforms plus blog and email behind a per-post review gate. Set a Radar alert on a topic you own, and the loop becomes: Radar catches the moment, Kompozy produces and ships your response before the conversation moves on.
Radar is a podcast search engine and intelligence platform announced August 26, 2026 by Particle. It transcribes and indexes podcast audio — more than 130,000 shows, adding about 20,000 episodes a day — and exposes it as structured, searchable data via an API and an MCP endpoint so people and AI agents can find what was said on air.
Its highest-volume customers are hedge funds mining spoken conversations for signals, alongside AI search platforms, data resellers, journalists, and researchers. Creators can use it as a research and monitoring layer to spot quotes and trends, but it is a data tool, not a content-production tool.
At launch Particle listed a Consumer plan at $29/month per seat and a Business plan at $399/month including 20 seats, with API pricing quoted custom based on usage. Confirm current pricing on Particle's own pages before you rely on it.
No. Radar finds, transcribes, and structures podcast content — it writes no posts, edits no video, and publishes to no platform. To turn a quote or trend it surfaces into finished, multi-platform content, pair it with a generation-and-publishing engine like Kompozy.
Use Radar to catch a quote, clip, or trend from the podcasts your audience listens to, then paste that into Kompozy Quick Ingest. Kompozy generates a Persona Short, carousel, quote graphic, text posts, a blog, and a newsletter in your brand voice and schedules them across the eight social platforms plus blog and email.