Company mention data across podcasts, Substack and Bluesky
What podcasts and newsletters say about any public company
Each mention of a monitored company, keyed to ticker and CIK, with the passage, the source, the speaker on podcasts, and daily counts and trending rankings.
featured in
Subalytics reads new podcast transcripts, Substack posts and Bluesky posts and records every mention of a monitored public company. Each mention is a row you can query: which company, where it appeared, the words around it, how it was matched and how confident the match is.
Counts roll up by day or week and by source, and the trending endpoint ranks companies by mention volume or by how much that volume changed. The monitored list covers 20,000+ companies, each with ticker, CIK, exchange, sector and industry.
One mention, fully described
From the entity-mentions endpoint
| Field | Type | What it holds |
|---|---|---|
mention_id | string | Stable ID for the mention |
symbol, company_name | string | The company, keyed by ticker |
source | string | podcast, substack or bluesky |
content_id, content_url | string | The episode or post, and a link to the original |
sub_id | string | The podcast or creator, joinable to creator and audience data |
match_type, matched_text | string | How it matched: cashtag, company name, alias, product or ticker, and the exact text |
confidence | number | 0.5 to 1.0 |
snippet | string | The passage around the mention |
start, end | number | null | Podcasts only: seconds from the start of the audio |
published_utc, created_at, updated_at | string | When it was published, first found and last changed |
{
"mention_id": "c07e5b1a94d2f836",
"symbol": "META",
"company_name": "Meta Platforms, Inc.",
"source": "podcast",
"content_id": "c41f7a09e2b85d13",
"sub_id": "a1b2c3d4e5",
"published_utc": "2026-09-24T16:38:09Z",
"match_type": "product",
"matched_text": "instagram",
"confidence": 0.78,
"snippet": "and instagram is basically where every small brand does its marketing now",
"start": 1834.2,
"end": 1841.9,
"created_at": "2026-09-25T07:15:03Z"
}Mention volume over time
The mention-stats endpoint returns a daily or weekly series for each company, split by source, with the number of pieces of content and the number of distinct creators or podcasts behind the mentions. A rise in mentions from many different shows reads differently from one show repeating a name, and the series lets you tell them apart.
Trending companies
Rank companies by mention volume or by change against the previous window of the same length. Filter by source (podcasts, Substack or Bluesky) and by sector, and set a minimum number of mentions to cut noise.
How matching works
- Five match types: cashtag ($TSLA), company name, alias, product name and ticker.
- Each mention has a confidence score from 0.5 to 1.0. Daily and weekly counts include only mentions at 0.7 or above.
- Podcast mentions return only the passage with the mention and its timestamps, not the whole transcript.
- Past content is re-checked as matching improves, so mentions can be added, re-scored or removed. The docs explain how to stay in sync.
Freshness
| Source | When mentions appear | Notes |
|---|---|---|
Bluesky | Within minutes | Full post text available |
Substack | Each collection run | Each post lists every company it mentions |
Podcasts | Within a few hours of the daily 05:00 UTC run | Passage, timestamps and speaker for each mention |
Who uses company mention data
Financial institutions
Track narrative and events for a coverage list, and use mention series in research and models.
Media-intelligence platforms
Add podcast and newsletter mentions of companies to monitoring products.
Investor relations and PR teams
See where your company and peers come up on podcasts and in newsletters.
FAQ
Common questions
Public companies on the monitored list, available through the entity-companies endpoint with ticker, CIK, exchange, sector and industry. The coverage page breaks the list down by sector and exchange.
Every mention records its match type and a confidence score, so you can set your own threshold. Counts use 0.7 and above, and past content is re-checked as matching improves.
No. Each mention comes with the passage, the source and the speaker on podcasts, so your team or your models can judge tone directly.
Full transcripts are part of podcast data access. The mention endpoints return the passage that contains the mention and its timestamps.
The standard API starts from when each source was first tracked. Historical data can be provided on request.
Contact us
Have a question or a custom use case?
Tell us what you're trying to monitor or search across, and we'll get back to you within a business day.
See mentions for your coverage list
Send us the tickers you follow and the sources you care about. We'll enable the entity endpoints for your team.