LIVE MENTIONS

AI DATA CENTERS"electricity demand could more than double to 945 terawatt-hours by 2030"EYFEDERAL RESERVE"a committee split between holding and hiking, with cuts still off the table"PIMCO PODAI VALUATIONS"AMD trades at 185 times earnings, and names like Palantir are in the stratosphere"THE DSR NETWORKOIL & ENERGY"the Strait of Hormuz carries nearly a fifth of the world's oil exports, keeping supply risk elevated"THE DAILY FINANCE BRIEFGLP-1 DRUGS"cutbacks from weight-loss drugs could cost packaged food up to $21 billion this year"MARKETPLACECOMMERCIAL REAL ESTATE"an $875 billion wall of debt is refinancing from sub-4.3% into 6% and higher"REAL ESTATE ESPRESSOAI DATA CENTERS"electricity demand could more than double to 945 terawatt-hours by 2030"EYFEDERAL RESERVE"a committee split between holding and hiking, with cuts still off the table"PIMCO PODAI VALUATIONS"AMD trades at 185 times earnings, and names like Palantir are in the stratosphere"THE DSR NETWORKOIL & ENERGY"the Strait of Hormuz carries nearly a fifth of the world's oil exports, keeping supply risk elevated"THE DAILY FINANCE BRIEFGLP-1 DRUGS"cutbacks from weight-loss drugs could cost packaged food up to $21 billion this year"MARKETPLACECOMMERCIAL REAL ESTATE"an $875 billion wall of debt is refinancing from sub-4.3% into 6% and higher"REAL ESTATE ESPRESSO

For hedge funds & private equity

The market intelligence most desks are missing.

CEOs, politicians, regulators, and analysts talk for hours on podcasts every day, on the record and in public. Particle turns 125,000+ of those shows into structured data, searchable within minutes of airing, and pipes it straight into your models and your stack.

$10 in free credit to start≈ 1,000 requests to evaluate the corpus

NVIDIALIVE

Nvidia Corp · nvidia.com

THE DSR NETWORKDean Baker

“Look at the prices of the AI companies, Nvidia and the others heavily involved in AI, like Google and Meta.”

THE DSR NETWORKDavid Rothkopf

“AMD's PE ratio is 185, and there are others like Palantir that are also in the crazy stratosphere.”

THE CTO PODCASTLucas

“They're using Nvidia GPUs co-located with storage nodes to run small models on the fly.”

Capabilities

Four ways to work the corpus.

Search by company, by theme, or by entity, and get alerted the moment something airs. Each result is cited back to the exact quote, speaker, and episode.

MentionsTrack a company or person by name. Each mention comes with the exact quote, the speaker, and the timestamp.

ThemesSearch a thesis or sector by meaning with semantic search, not just keywords. Surface where a topic is discussed and read what the people closest to it actually said.

AlertsWatch a company, a person, or a theme, and get an email the moment it airs, filtered by relevance, language, and audience reach.

EntitiesPeople and companies linked into one graph. Resolve a name once, then traverse to its competitors, products, and past appearances.

Live from the corpus

Real output, sourced and dated.

Here are two semantic searches run through our data, “GLP-1 exposure” and “commercial real estate,” with each line speaker-attributed and timestamped so you can verify it against the audio.

GLP-1 EXPOSURELIVE

THE BIDLisa Yang

“Obesity drugs are bringing about one of the most profound structural shifts in consumption that I've seen.”

MARKETPLACEHenry Epp

“GLP-1 cutbacks could cost the packaged food industry up to $21 billion this year.”

MARKETPLACEKimberly Adams

“GLP-1 use could shave up to 2.7% off grocery store sales this year.”

Ranked by relevance across 125,000+ shows.

COMMERCIAL REAL ESTATELIVE

REAL ESTATE ESPRESSOVictor Menasce

“An $875 billion wall of debt originated below 4.3% now has to refinance at 6% or higher, a 190 basis point shock.”

REAL ESTATE ESPRESSOVictor Menasce

“In office, the CMBS delinquency rate crossed 12%, levels last seen during the financial crisis.”

FINANCIAL SERVICES FOCUSMichael Cohen

“Loans originated between 2017 and 2023, the majority of them are over-levered.”

Ranked by relevance across 125,000+ shows.

Access

Query it from your own stack.

The same corpus behind Radar is available as a REST API and over MCP, on one key. Pull mentions into a signal pipeline, run a semantic search from a notebook, or point a research agent at it and let it ask in plain language.

MENTIONS · RESTapi.particle.pro

curl "https://api.particle.pro/v1/podcasts/mentions?company_id=nvidia" \
  -H "X-API-Key: $PARTICLE_API_KEY"

# each line naming the company, with speaker, show, and timestamp

REST

Endpoints for mentions, semantic search, transcripts, episodes, guests, and the entity graph. JSON or LLM-tuned markdown via output_format.

MCP

Point an agent at mcp.particle.pro and it queries in natural language. Works with Claude Code, Codex, Cursor, and anything that speaks MCP.

FAQ

Frequently Asked Questions

Where does the data come from, and what's covered?

We ingest and transcribe the audio of 125,000+ podcasts, including finance, policy, and industry shows, then detect the people and companies named. Coverage is mostly US and English today, and expanding continuously.

What does it cost to start?

$10 in free credit, roughly 1,000 requests, to evaluate. After that it's $29/mo for 10,000 requests, $399/mo for 100,000, or custom pricing for larger volumes backed by SLAs.

How is this different from AlphaSense, Tegus, or an expert network?

Those index filings, earnings calls, and paid expert interviews. Particle covers the 125,000+ podcasts where the same executives, officials, and analysts talk candidly and publicly, and it comes back as structured data you can query rather than documents you have to read.

How fresh is it?

New episodes are transcribed and queryable within minutes of airing, and alerts fire in near-real-time. When a CEO says something on a morning show, it's in the corpus before the day is out.

REST or MCP?

Both, on the same key. REST at api.particle.pro with an X-API-Key header, or point an agent at mcp.particle.pro and it queries in natural language.

Can we see it working on our names first?

Yes. Book a call and we'll run your tickers and themes through the corpus live, then talk through how it would sit in your workflow.

Get started

Glean insights from across the podcast landscape.

Take $10 of credit and make your first call in minutes, or have us run your names first.

Prefer the dashboard? Try Radar for free →