Particle

Podcasts

Visit website

Podcast intelligence: podcast & episode search, transcripts, speakers, entity mentions, sponsor & advertising data, alerts and embeds.

About Particle

Particle is a podcast intelligence API that transcribes, diarizes, and speaker-identifies podcast episodes shortly after they air, covering more than 100,000 shows with roughly 19,000 episodes processed daily. It provides full transcripts with speaker labels and word-level timestamps, entity extraction (people, companies, topics), semantic and keyword search across transcripts, guest and topic metadata, brand-safety and political-bias ratings, and rankings across the Apple Podcasts Top 200 in 130+ verticals. It also offers sponsorship intelligence that detects and maps ad reads to canonical brands, including placement type (pre-roll vs. mid-roll, host-read vs. pre-recorded) and an ad leaderboard.

The product is aimed at developers and agent builders: it exposes a REST API and an MCP server that connects to clients such as Claude Code, Claude Desktop, Cursor, and VS Code, and integrates with third-party platforms including Exa Connect and Lightfield. It supports configurable alerts (as-it-happens, daily, or weekly digests) delivered via email, Slack, or webhooks when tracked entities, keywords, or guests appear in new episodes, and provides embeddable HTML clips with synced audio and text for individual segments.

Key features

Transcribes, diarizes, and speaker-identifies 100,000+ podcasts within minutes of airing
Full-text search across transcripts by entity, keyword, or semantic match
Sponsorship intelligence tracking ad reads, placements, and canonical brand mapping
Real-time, daily, or weekly alerts for tracked entities, keywords, or guest appearances
Rankings across the entire Apple Podcasts Top 200 in 130+ verticals
MCP server for connecting to Claude, Cursor, and other AI agents

Frequently asked questions

What platforms or clients does Particle integrate with?

Particle offers a REST API and an MCP server that connects to Claude Code, Claude Desktop, Cursor, VS Code, and other MCP clients. It also connects to research agents via Exa Connect and the Lightfield agent platform.

How is data accessed?

Data is accessed via a REST API using an API key, with endpoints for mentions, advertising leaderboards, and rankings.

How fresh is the podcast data?

New episodes are transcribed, diarized, and speaker-identified within minutes after airing, and the ad leaderboard and rankings are updated daily.

Who is Particle for?

It is for developers and agent builders who need podcast transcripts, search, sponsorship data, or alerts, such as those building AI agents or tracking brand and entity mentions across podcasts.

What kind of metadata is included with each podcast?

Each episode includes canonical entities for guests, hosts, and companies, topics, audience size estimates, brand-safety ratings, and political-bias ratings.