Search podcast transcripts by API
Podcast transcript data you can filter, join and backtest
Timestamped transcripts of new episodes from 250K+ tracked podcasts, with speakers identified by name, role, title and company. Transcribed daily and delivered as JSON.
featured in
Subalytics turns podcast episodes into structured data you can search and query. Every day it transcribes new episodes from 250K+ tracked podcasts, a curated list of news, business, sports and technology shows, and splits each transcript into timestamped segments with the speaker for each.
Funds use the transcripts to find what executives and analysts said about a company. Media-intelligence platforms use them to add podcasts to their monitoring. Both get the same API, the same fields and the same daily schedule.
What's in a transcript
One record per episode, split into speaker segments
| Field | Type | What it holds |
|---|---|---|
episode_sub_id | string | Stable episode ID, shared with the episodes and entity endpoints |
podcast | object | sub_id and podcast name |
episode | object | Title, publish time, audio URL and episode link |
language | string | null | Language detected from the audio |
duration_seconds | number | null | Measured audio length |
speakers | object | Each speaker's name, role (host, co-host, guest), title and company, where identified |
segments | array | Start and end time in seconds, text and speaker for each segment |
created_at / updated_at | string | When the transcript was first produced and when it last changed |
{
"episode_sub_id": "c41f7a09e2b85d13",
"podcast": { "sub_id": "a1b2c3d4e5", "podcast_name": "Example Business Show" },
"episode": { "episode_title": "Rate Cuts, Robotaxis and the Week in Markets", "published_at": "2026-09-24T16:38:09Z" },
"speakers": {
"SPEAKER_00": { "name": "Jane Host", "role": "host", "title": "journalist", "company": "Example Media" },
"SPEAKER_01": { "name": "Sam Guest", "role": "guest", "title": "economist", "company": null }
},
"segments": [
{ "start": 1.0, "end": 9.72, "text": "Welcome back to the show. Big week in markets.", "speaker": "SPEAKER_00" },
{ "start": 10.1, "end": 17.4, "text": "It really was. Let's start with the rate decision.", "speaker": "SPEAKER_01" }
],
"created_at": "2026-09-25T06:12:47Z",
"updated_at": "2026-09-27T05:48:31Z"
}Filter by show, episode and date
Pull exactly the episodes you need
- Filter podcasts by category, language and the date of their latest episode.
- Filter episodes by podcast, publish date or the date they were transcribed.
- Sync transcripts that are new or changed since your last pull with updated_from.
- Request the full transcript, or a summary record, for any episode.
Find executive interviews
Speakers carry a title and a company when they can be identified, so a CEO's appearance on a business podcast is findable by company as well as by name. Identification is automatic and best-effort, and any of the four fields can be empty.
Company mentions, joined to tickers
Every mention of a monitored public company in a transcript is also available as its own record, keyed to ticker and CIK, with the passage, the speaker and its start and end time in the audio. The same mention data covers Substack and Bluesky.
Coverage and freshness
| Item | Value | Notes |
|---|---|---|
Tracked podcasts | 250K+ | Curated news, business, sports and technology shows; more can be added on request |
Update schedule | Daily | New episodes usually appear within a few hours of the 05:00 UTC run |
History | Since tracking began | Episodes since each podcast was first tracked, not full back catalogues; historical data available on request |
Built for point-in-time research
Each episode records when the podcast published it and when its transcript became available in Subalytics. Backtests that filter on the availability time only use transcripts that existed on that date. Transcripts can change later, for example when speaker names are filled in, and updated_at shows when.
Who uses podcast transcript data
Financial institutions
Hedge funds, asset managers and research teams follow what executives and analysts say about the companies they cover.
Media-intelligence platforms
Monitoring and intelligence products license the feed to add podcasts to their coverage.
Creator-intelligence teams
Partnership and research teams find podcast hosts and guests by topic.
How it's delivered
A REST API with an OpenAPI 3.1 specification, JSON responses and cursor pagination. Sync daily with updated_from, or ask about bulk and historical deliveries.
FAQ
Common questions
Transcription runs every day at 05:00 UTC. New episodes and their transcripts usually appear within a few hours of that run.
The standard API includes episodes published since Subalytics started tracking each podcast. Historical data can be provided on request.
Automatically, on a best-effort basis. Each speaker can have a name, a role such as host or guest, a title and a company, and any of those can be empty when they couldn't be identified. When names are filled in later, the transcript's updated_at changes.
Yes. The tracked list is curated, and shows can be added on request.
With podcast data access you get full transcripts. The company mention endpoints return only the passages that mention a company.
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.
Get podcast transcripts into your research
Tell us which shows, topics or companies you need, and we'll enable the matching endpoints on your API key.