How hedge funds use podcast transcripts for research

In this post

• Find what executives in a niche industry are saying.

• Find experts who have already spoken about a topic before you book a call, from oncologists to freight and commodity analysts.

• Follow the economy through what Fed presidents and top CEOs are saying.

• Examples from AI power demand, farm equipment, radiopharmaceuticals, freight, cocoa, memory chips, the Fed and big banks.

Research teams already read earnings call transcripts and book calls with industry experts to hear from people close to a business. Podcasts add more of those people, speaking at length and on the record: a utility's strategy chief on how much data center demand will get built, a farm equipment CEO on whether farmers are ready to buy, two radiation oncologists on what limits a new kind of cancer treatment, and a cocoa analyst on the surplus he says the market is ignoring.

That's useful for research, and it's hard to find because it's audio, spread across thousands of shows.

Particle makes podcasts searchable. We actively transcribe 145,000+ podcasts, and new episodes are typically searchable within minutes of airing. You can reach them through an MCP server, so they sit next to your other sources in Claude, ChatGPT or Cursor, through a REST API, or, on Enterprise plans, as a real-time stream of new episodes. If you'd rather search by hand, Radar is our podcast search engine in the browser, and it's where the episode links in this post open.

The searches below fall into three groups: executives in niche industries, experts in niche fields, and the big picture from Fed presidents and large-company CEOs. The video walks through all three:

1. Executives in niche industries

Executives talk about demand, pricing, and capacity in their own industry on trade podcasts, industry shows, and business news programs. Connect Particle to your MCP client (see "Set it up" below), then describe who you want to hear from in plain language. Good prompts cover a few things:

• Industry and role: "utility executives," "farm equipment dealers and manufacturers."

• Topic: "AI data center demand," "tractor demand this season."

• Timeframe: "in the last month," or "since August."

• A name, when you have one: Particle resolves it to a company or a person in its knowledge graph before it searches, so you get the company you meant rather than everything that sounds like it.

Example: AI power demand

Ask: What are utility executives saying about data center load growth?

One of the speakers it finds is Geoffrey Bailey, Vice President of Corporate Strategy and Chief of Staff to the CEO at Oncor Electric Delivery, which runs the largest transmission and distribution system in Texas. On The Sustainability Agenda (Aug 27, 2026), he puts numbers on the requests. At the end of the second quarter, Oncor's queue of large commercial and industrial customers asking to connect was 298 gigawatts, and 282 gigawatts of that was data centers. Oncor's system peaks at 33 gigawatts. Then he says: "So we are the first to say there's no way in the world that, you know, two hundred and eighty-two gigawatts of, of data center load actually materializes."

That's Oncor's own strategy chief saying its data center queue won't all get built.

Example: farm equipment

Ask: What are farm equipment makers and dealers saying about tractor demand?

Two of the results point in different directions:

• Eric Hansotia, chairman, president and CEO of AGCO, speaking at the Farm Progress Show, in a clip on the Farm Equipment Podcast (Sep 11, 2026): "The dealers have enough inventory, and the farmers are wanting to buy."

• Bob Larson, farm news host for the Ag Information Network, on The Agribusiness Update (Aug 18, 2026): "U.S. agricultural tractor sales dropped nearly 11% in July compared to last year", citing data from the Association of Equipment Manufacturers. AEM's release puts the decline at 10.9%.

The same search gives you the CEO's view and the industry's numbers next to each other.

This also works in other industries:

• Hospitals. What are health system CEOs saying about reimbursement? Amy Mansue, CEO of Inspira Health, on Becker's Healthcare Podcast (Aug 26, 2026): "I don't think there's a hospital CEO or health system CEO in the country that isn't thinking about the reimbursement challenges and opportunities that are before us."

• Restaurants. What are restaurant industry leaders saying about the consumer? Michelle Korsmo, president and CEO of the National Restaurant Association, on Schwab Network (Sep 24, 2026): "we know that the consumer confidence numbers are definitely trending downward", though she sees restaurant hiring as a better sign.

2. Experts in niche fields

Executives tell you what they're seeing. Experts can tell you why. Before you book an expert call, you can check who has already spoken about the topic in public, and what they said. Describe the field and the seniority you want, such as "directors at academic cancer centers" or "commodity analysts at banks."

Example: radiopharmaceuticals

Ask: Which experts are talking about radiopharmaceuticals?

One episode of RadOnc on the Run (Aug 26, 2026), a radiation oncology podcast, had two people who lead radiopharmaceutical work at academic centers:

• Mallika Marar, director of theragnostics in Stanford's radiation oncology group at the time of the episode: "At least in my practice, many patients have to drive hours to get to us for treatment."

• Neil Taunk, director of imaging sciences in radiation oncology at Penn Medicine, who leads many of Penn's phase one radiopharmaceutical therapy trials, built on Marar's point: between ASTRO, the radiation oncology society, and manufacturers, there's "a massive push to make sure that the workforce is trained", from physicians to medical physicists and nuclear medicine technologists.

Both point to what limits how fast these treatments can reach patients: how far patients have to travel, and the push to train enough staff to run the programs.

It's not only doctors. The same kind of search finds analysts in other fields:

Each link opens the episode in Radar at the line where it was said.

3. The big picture

For the economy as a whole, ask the people who see the most of it: Fed presidents and the CEOs of large companies.

The Fed's view. Ask: What are regional Fed presidents saying about the economy?

• Neel Kashkari, president of the Minneapolis Fed, on Fox News, replayed on Bloomberg News Now (Sep 21, 2026): "inflation is still too high. So my colleagues and I voted unanimously to raise interest rates."

• Mary Daly, president of the San Francisco Fed, on Bloomberg Talks (Aug 20, 2026), on what CEOs tell her when she asks about their plans to cut back: "They know what they would do, but they still see that cautious optimism of trying to meet output growth where it is"

What companies see. Then ask: What are big-company CEOs saying about the economy?

• Brian Moynihan, CEO of Bank of America, on Cats Roundtable (Aug 16, 2026), on what Bank of America customers spent in July: "they moved 5% more money out of their accounts or used their credit cards and debit cards to buy things than they did last year… that's consistent with a solidly growing U.S. economy"

• Jamie Dimon, CEO of JPMorgan Chase, on CNBC's Squawk Box Asia, replayed on Power Lunch (Sep 22, 2026): "I'm hoping that inflation stays here and starts to come down. I, I don't bet on that."

Put together, you get the Fed's case for raising rates next to how two big-bank CEOs see growth and inflation, in their own words.

Other ways research teams use it

• Pull what's been said about one company or person. "What has been said about [company] on podcasts?" Particle resolves the name to an entity first and returns the mentions grouped by episode, so you get the company you meant rather than everything that sounds like it.

• Set alerts. "Alert me when [company] is mentioned on a podcast." Each alert watches one company, person, brand or topic across the indexed catalog, and sends matches as they happen or as a daily or weekly digest, with the clip and transcript attached. Paid plans include alerts: 1 on Individual, 5 on Business.

• Track an expert's appearances. "Which podcasts has [name] been a guest on?" Particle keeps an appearance history for each guest, including how many shows they've been on and their first and most recent appearance.

• Spot a press tour. "Which executives are making the rounds on podcasts right now?" By default, Particle's trending-guest list counts people who appeared on two or more different shows in the last 30 days.

• See how often a topic comes up. "How many podcast episodes discussed [topic] each month this year?" Particle counts matching episodes by day, week or month.

• Take new episodes as a stream. On Enterprise plans, the real-time firehose delivers new episodes to your own systems, for teams that want the data in-house rather than querying it.

Set it up

The quickest way to get started is to hand the setup to your assistant. In Claude or ChatGPT, paste:

Read particle.pro/agents.md and connect me to Particle over MCP.

The assistant reads that page, walks you through its own settings, and asks you to sign in when it gets there. In ChatGPT, that includes turning on developer mode, which needs a paid plan. If you would rather follow written steps, the setup guide has every client, with one-click installs for Cursor and VS Code.

To do it by hand, the server is https://mcp.particle.pro, and you sign in through the browser the first time:

On Claude Team and Enterprise plans, an Owner or Primary Owner adds the connector once under Organization settings before anyone else can connect it. And on ChatGPT Business, only workspace admins and owners can turn on developer mode; on Enterprise and Edu, admins decide who gets it.

Prefer your own stack? The same search is one REST call, GET /v1/podcasts/episodes/search with semantic_search, since and limit, authenticated with an X-API-Key header. Create an account, generate a key, and the docs have the rest.

FAQ

What's indexed? 145,000+ podcasts and counting, including the Apple Podcasts Top 200 in the US across 130+ English-language verticals, plus independent and trade shows like the ones in this post.

How current is the data? Most episodes are transcribed, speaker-labeled and searchable within minutes of publication.

Where do these quotes come from? Published podcast episodes. Each quote in this post links to the public episode it came from, at the line where it was said.

What does it cost? Individual is $29 a month for 10,000 requests, one seat and one alert. Business is $399 a month for 100,000 requests, 20 seats, five alerts and the premium endpoints (ad intelligence, publisher landscape, brand safety and suitability). Enterprise is custom, and adds a real-time firehose, high request volumes with SLAs, custom integrations, access to all endpoints and dedicated support: api@particle.pro.

Is there a free trial? Yes. Picking a plan comes with $10 in free credits, about 1,000 requests, and you are not charged until you have used them.

Do the episode links work without an account? Anyone can open them and read the transcript around the highlighted line. Reading the rest of an episode needs an account.

Can we build this into our own tools? Yes. Particle's API terms cover the permitted uses of data in internal tools, dashboards and analytics platforms, as well as external-facing applications. Certain uses are not allowed, including the resale of data, bulk downloading or storage beyond what is reasonably necessary for display, and training of machine learning models. Any attribution information that is included in API output must also be displayed to end users.

What's Radar? Radar is Particle's search engine for podcasts: entity, keyword and semantic search in the browser, with no code. The episode links in this post open there.

Start researching

Find out what executives and experts in your tracked sectors are saying. Get started with $10 in free credits (about 1,000 requests) at particle.pro.