Episodes

Discover and filter episodes across the catalog, with rich per-episode sub-resources.

The cross-podcast episode endpoint is the primary discovery tool. Filter by podcast, entity, company, language, date range, or duration. Every episode comes with sub-resources for transcripts, segments, clips, speakers, entities, and topics.

Tracking new episodes as they’re ingested? Don’t poll this list with published_after — use the episode feed, a resumable poll that returns each new episode exactly once, or the real-time episode stream (Enterprise).

Available to MCP agents as particle_podcast_list_episodes and (per-episode) particle_podcast_get_episode.

List episodes

curl

curl "https://api.particle.pro/v1/podcasts/episodes?entity_id=sam-altman&limit=3" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Response (truncated)

{
  "data": [
    {
      "id": "78cgekLUjCJBUZbj3s5K8Y",
      "title": "WHCD Shooting Aftermath, Musk and Altman Face-Off, Spirit Airlines Bailout",
      "podcast": { "id": "QpMz7GYKfSNuUa6zKXA4Q", "title": "Pivot" },
      "published_at": "2026-04-28T10:00:00Z",
      "duration_seconds": 4206,
      "has_transcript": true,
      "segment_count": 21,
      "clip_count": 8,
      "entity_count": 146,
      "speakers": [ /* … */ ]
    }
    // …
  ],
  "has_more": true,
  "cursor": "…"
}

The has_transcript, segment_count, clip_count, and entity_count fields tell you what enrichment data is available before you fetch any sub-resource.

Filter parameters

Parameter	Description	Example
podcast_id	Slug, ID, or numeric iTunes ID; restrict to one podcast	?podcast_id=pivot
entity_id	Slug or ID; episodes featuring or mentioning the entity	?entity_id=sam-altman
company_id	Slug, domain, or ID; episodes featuring a company	?company_id=nvidia
language	ISO 639-1 code	?language=en
published_after	ISO 8601 timestamp	?published_after=2026-04-01T00:00:00Z
published_before	ISO 8601 timestamp	?published_before=2026-04-30T00:00:00Z
has_transcript	Limit to transcribed episodes	?has_transcript=true
min_duration / max_duration	Bounds in seconds	?min_duration=1800&max_duration=7200

Holding an Apple Podcasts episode ID (the ?i= value in an Apple Podcasts URL) instead? That resolves through GET /v1/podcasts/episodes/lookup, not a filter here.

Combine freely — for long-form transcribed Sam Altman episodes from this month, for example:

curl "https://api.particle.pro/v1/podcasts/episodes?\
entity_id=sam-altman&\
has_transcript=true&\
min_duration=1800&\
published_after=2026-04-01T00:00:00Z&\
limit=10" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Get a single episode

curl

curl "https://api.particle.pro/v1/podcasts/episodes/78cgekLUjCJBUZbj3s5K8Y" \
  -H "X-API-Key: $PARTICLE_API_KEY"

The full Episode response is documented in the API reference.

Episodes for a specific podcast

A convenience shape of list-episodes filtered by podcast:

curl "https://api.particle.pro/v1/podcasts/pivot/episodes?limit=10" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Sub-resources

Every episode exposes its enrichment data as sub-resources:

Endpoint	Returns
GET .../episodes/{id}/transcript	Diarized dialogue (full transcript)
GET .../episodes/{id}/transcript/words	Word-level timestamps
GET .../episodes/{id}/transcript/mentions	Lines around mentions of an entity
GET .../episodes/{id}/segments	Structural sections (intros, ads, topic discussions)
GET .../episodes/{id}/clips	Highlight clips
GET .../episodes/{id}/speakers	Identified speakers with speaking duration
GET .../episodes/{id}/entities	Mentioned entities ranked by salience
GET .../episodes/{id}/topics	Topic classifications

Speakers

curl "https://api.particle.pro/v1/podcasts/episodes/78cgekLUjCJBUZbj3s5K8Y/speakers" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Response (truncated)

{
  "data": [
    {
      "name": "Kara Swisher",
      "role": "HOST",
      "speaking_duration_seconds": 1674.51,
      "entity_slug": "kara-swisher"
    },
    {
      "name": "Scott Galloway",
      "role": "HOST",
      "speaking_duration_seconds": 1918.24,
      "entity_slug": "scott-galloway"
    }
    // …
  ]
}

By default this returns the people taking part in the conversation — HOST, GUEST, PANELIST and CORRESPONDENT. Use role to widen or narrow the set; values are case-insensitive, and roles always come back in uppercase.

curl "https://api.particle.pro/v1/podcasts/episodes/78cgekLUjCJBUZbj3s5K8Y/speakers?role=host,soundbite_speaker" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Response (truncated)

{
  "data": [
    {
      "name": "Kara Swisher",
      "role": "HOST",
      "speaking_duration_seconds": 1674.51,
      "entity_slug": "kara-swisher"
    },
    {
      "name": "Yuval Noah Harari",
      "role": "SOUNDBITE_SPEAKER",
      "speaking_duration_seconds": 50.30,
      "entity_slug": "yuval-noah-harari"
    }
    // …
  ]
}

Speaker roles

Every speaker carries exactly one of these roles. The four in the default set are marked; the rest require naming them in role.

Role	Meaning
HOST	Runs the show — guides the discussion and engages with guests. Default
GUEST	Invited for this episode to provide insight, expertise, or entertainment. Default
PANELIST	Regular or semi-regular contributor in a roundtable format. Default
CORRESPONDENT	Reporter or field contributor filing a segment. Default
MODERATOR	Guides a debate or multi-guest discussion without hosting the show.
NARRATOR	Structured narration, common in documentary-style shows.
ANNOUNCER	Show and station identifications, intros, and network tags.
VOICE_ACTOR	Performs a scripted role, common in fiction podcasts.
SOUNDBITE_SPEAKER	Appears via a played clip or archival excerpt rather than in the room.
AUDIENCE	Callers, listeners, and audience members.
ADVERTISER	Reads promotional or sponsor content.
PRODUCER	Production staff heard on mic — producers, editors, engineers.
UNKNOWN	Speaks in the episode but could not be identified.
OTHER	Recognized as a distinct speaker but fitting none of the above.

This list is exhaustive and stable, across the whole archive — you can branch on role without a fallback case.

The entity_slug (when present) bridges to the knowledge graph.

Entities

Returns people, organizations, places, products, and concepts mentioned in the episode, ranked by salience — a relative relevance score for that episode where higher values indicate the entity is more central to the discussion.

curl "https://api.particle.pro/v1/podcasts/episodes/78cgekLUjCJBUZbj3s5K8Y/entities" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Response (truncated)

{
  "data": [
    {
      "entity": { "id": "1GmOP1C2UZtpnHKPoc", "slug": "openai", "name": "OpenAI" },
      "salience": 0.0061,
      "occurrences": 11
    },
    {
      "entity": { "id": "1GmOP1C3KLh", "slug": "anthropic", "name": "Anthropic" },
      "salience": 0.00024,
      "occurrences": 10
    },
    {
      "entity": { "id": "17PzxG1t12xzno", "slug": "sam-altman", "name": "Sam Altman" },
      "salience": 0.00016,
      "occurrences": 5
    }
    // …
  ]
}

For the actual dialogue around mentions, see transcripts → mentions.

Topics

curl "https://api.particle.pro/v1/podcasts/episodes/78cgekLUjCJBUZbj3s5K8Y/topics" \
  -H "X-API-Key: $PARTICLE_API_KEY"

Topics are drawn from the hierarchical topics taxonomy — useful for routing episodes to category-specific feeds.

Related

• Transcripts — dialogue, words, mentions, SRT
• Segments & clips — structural breakdown and highlights
• Knowledge graph → entities — follow speakers and topics across the catalog