clip_id for one clip’s full detail (description, social-hook intro, speaker, audio URL), plus include: ["transcript"] for its dialogue.
For text-based clip discovery — finding clips about a topic or entity — use particle_podcast_search_transcripts instead: matching clips arrive inline on each search result. A known episode’s full clip list also comes from particle_podcast_get_episode with include: ["clips"].
Inputs
Output
Listing mode:## Highlight clips (N) with one bullet per clip — **Title** (TYPE, score N) — Episode Title on Podcast Title (episode-slug) @ 100s–160s — clip ID: <id>. Episode slugs feed the episode tools; clip IDs feed the clip_id detail path. When more pages exist, a horizontal rule and a **Cursor:** line are appended.
Detail mode (clip_id set): the clip title as an H2 with **Clip ID:**, **Type:**, **Engagement score:**, **Speaker:**, **Episode:**, **Span:**, and **Audio:** rows, the description paragraph, the **Social hook:** line, and — with include=["transcript"] — a ### Transcript section of **Speaker:** text dialogue lines.
Example
Related
- REST equivalents:
GET /v1/podcasts/clips,GET /v1/podcasts/clips/{id},GET /v1/podcasts/clips/{id}/transcript. - Embed a clip on a web page with the embed endpoints.