Podscan is the podcast search engine that indexes millions of episodes with full transcripts. Search for any topic and find exactly which podcasts discussed it — with timestamps, quotes, and context. For researchers, marketers, and anyone tracking what's being said in audio content, Podscan is invaluable.
Graphlit integrates Podscan as a native search backend. Search podcasts through Graphlit and results are automatically ingested — transcripts processed, entities extracted, and content connected to your knowledge base.
This means podcast intelligence becomes part of your searchable knowledge, alongside documents, web content, and everything else.
Table of Contents
- TL;DR — Quick Comparison
- What Podscan Does Well
- What Graphlit Adds
- The Integration
- Use Cases
- When to Use Podscan Directly
- When to Use Podscan Through Graphlit
- Integration Example
TL;DR — Quick Comparison
What Podscan Does Well
Podscan solved a hard problem: making audio content searchable.
Massive Index
Millions of podcast episodes indexed with full transcripts. If it was said on a podcast, Podscan probably has it.
Full Transcripts
Not just titles and descriptions — actual transcripts with timestamps. Find the exact moment someone said something.
Topic Tracking
Monitor topics across the podcast ecosystem. See what's being discussed, by whom, and when.
Quote Discovery
Find specific quotes and statements. Great for research, competitive intelligence, and media monitoring.
API Access
Programmatic access to search and transcripts for building applications.
For anyone who needs to know what's being said in podcasts, Podscan is the answer.
What Graphlit Adds
Graphlit turns Podscan discoveries into connected knowledge:
Full Transcript Ingestion
Podscan finds the episodes. Graphlit ingests the complete transcripts, not just snippets.
Automatic Processing
Every podcast result is:
- Full transcript ingested
- Embedded for vector search
- Entity-extracted (speakers, guests, companies mentioned)
- Connected to your knowledge graph
Speaker and Guest Tracking
Extract who's speaking and who's being discussed. Track individuals across podcast appearances.
Cross-Content Search
Search podcasts alongside your documents, web research, emails, Slack conversations — everything unified.
Topic Monitoring Feeds
Set up automated searches that discover and ingest new podcast mentions. Monitor your brand, competitors, or topics automatically.
RAG with Podcast Sources
Ask questions and get answers sourced from podcast transcripts, properly cited.
The Integration
Podscan is available through Graphlit's SearchServiceTypes:
import { Graphlit, Types } from 'graphlit-client';
const client = new Graphlit();
// Search podcasts with Podscan
const results = await client.searchWeb(
"AI agent memory and context management",
Types.SearchServiceTypes.Podscan,
10
);
// Results include podcast episodes discussing this topic
// Ingest transcripts into knowledge base
for (const result of results.searchWeb?.results || []) {
await client.ingestUri(result.uri, result.title);
}
Automated podcast monitoring:
// Create a Podscan search feed
const feed = await client.createFeed({
name: "AI Podcast Mentions",
type: Types.FeedTypes.Search,
search: {
type: Types.SearchServiceTypes.Podscan,
text: "knowledge graphs artificial intelligence",
readLimit: 10
},
schedulePolicy: {
recurrenceType: Types.TimedPolicyRecurrenceTypes.Weekly
}
});
// New podcast mentions are automatically:
// - Discovered via Podscan
// - Transcripts ingested
// - Processed and embedded
// - Added to your knowledge base
Use Cases
Competitive Intelligence
Monitor what's being said about your company or competitors on podcasts. Get alerts when you're mentioned, with full context.
Research and Analysis
Track discussions of specific topics across the podcast ecosystem. See how narratives evolve over time.
Expert Discovery
Find podcast guests who discuss specific topics. Build lists of experts, influencers, and thought leaders.
Media Monitoring
PR and communications teams can track podcast mentions alongside traditional media.
Sales Intelligence
Know when prospects or target companies appear on podcasts. Understand their perspectives before reaching out.
Content Research
Content creators can see what's already been discussed and find unique angles.
When to Use Podscan Directly
Use Podscan directly when:
- Quick searches: One-off searches without persistence needs
- Browsing: Exploring what podcasts discuss a topic
- Alerts only: Just want notifications, not full ingestion
- Existing infrastructure: You have your own transcript processing pipeline
Podscan's web interface and API are great for direct podcast discovery.
When to Use Podscan Through Graphlit
Use Graphlit's Podscan integration when:
- Building knowledge bases: Podcast insights should be searchable long-term
- Entity tracking: Extract and connect speakers, guests, companies
- Cross-content search: Podcasts alongside documents and other sources
- Automated monitoring: Recurring searches with automatic ingestion
- RAG applications: Podcast content as sources for AI conversations
- Team access: Shared podcast intelligence across your organization
The integration turns podcast discovery into persistent, connected knowledge.
Integration Example
Podscan Direct: Search and Listen
import requests
# Search Podscan
response = requests.get(
"https://api.podscan.fm/search",
params={"q": "AI agent memory", "limit": 10},
headers={"Authorization": "Bearer ..."}
)
results = response.json()
# Results tell you which podcasts discussed this
for episode in results['episodes']:
print(episode['title'], episode['podcast_name'])
# Now what? Manual listening, manual note-taking...
# To build knowledge from podcasts:
# 1. Fetch full transcripts
# 2. Process and clean text
# 3. Generate embeddings
# 4. Extract entities (speakers, guests)
# 5. Store in vector database
# 6. Build search index
# 7. Connect to other content
Graphlit with Podscan: Podcast to Knowledge
import { Graphlit, Types } from 'graphlit-client';
const client = new Graphlit();
// Search podcasts with Podscan
const results = await client.searchWeb(
"AI agent memory architectures",
Types.SearchServiceTypes.Podscan,
10
);
// Ingest all discovered episodes
for (const result of results.searchWeb?.results || []) {
await client.ingestUri(result.uri, result.title);
}
// Podcast content is now:
// - Full transcripts ingested
// - Embedded for semantic search
// - Entities extracted (hosts, guests, companies)
// - Connected in knowledge graph
// - Searchable with everything else
// Set up automated monitoring
const feed = await client.createFeed({
name: "AI Memory Podcast Monitor",
type: Types.FeedTypes.Search,
search: {
type: Types.SearchServiceTypes.Podscan,
text: "AI memory frameworks",
readLimit: 10
},
schedulePolicy: {
recurrenceType: Types.TimedPolicyRecurrenceTypes.Weekly
}
});
// Search across podcasts + docs + web + everything
const contents = await client.queryContents({
search: "long-term memory for AI agents"
});
// RAG conversation with podcast sources
const response = await client.promptConversation(
"What are experts saying about AI agent memory on podcasts?",
conversationId,
{ id: specificationId }
);
// Response cites specific podcast episodes as sources
Summary
Podscan makes the podcast ecosystem searchable — millions of episodes with full transcripts, findable by topic, quote, or speaker.
Graphlit integrates Podscan as a native backend, adding:
- Full transcript ingestion
- Automatic embedding and entity extraction
- Speaker and guest tracking across episodes
- Unified search with all your other content
- Automated monitoring feeds
- RAG conversations with podcast sources
Use Podscan directly for quick podcast discovery. Use Podscan through Graphlit when podcast intelligence should become part of your searchable knowledge base.
Explore Graphlit Features:
- Web Scraping and Search — Content discovery
- Building Knowledge Graphs — Entity extraction
- Complete Guide to Search — Hybrid search
- Data Connectors — All integrations
Learn More:
Podcasts contain knowledge. Graphlit makes it searchable.