particle_podcast_search_transcripts

Semantic, keyword, or hybrid search over podcast transcripts — the single way to retrieve relevant dialogue, segments, and clips.

Search the podcast catalog by what is said in episodes — by meaning (semantic_search), by exact phrase (keyword_search), or both at once (hybrid ranking). This is THE way to retrieve relevant dialogue, segments, and clips: each result is one segment of one episode with bounded transcript windows pinpointing the highest-relevance lines, plus any highlight clips that overlap the segment, inline on the match.

This tool replaces the old search_dialogue and list_clips tools. There is no separate clip-search tool — relevant clips arrive on these matches. A known episode’s full clip list is particle_podcast_get_episode with include: ["clips"].

Segments vs clips

• Segments partition an episode’s transcript — where start_line/end_line are present, every spoken line belongs to exactly one segment and one segment’s end_line + 1 is the next one’s start_line. They are contiguous in transcript lines, not in wall-clock seconds: the seconds between one segment’s end_seconds and the next’s start_seconds contain no transcribed speech. These matches do not carry the line ranges themselves — fetch them with particle_podcast_get_episode and include: ["segments"], where their absence marks an episode segmented by an earlier version, a small share of which do leave lines uncovered. Search ranks segments and returns the matching ones.
• Clips are sparse, engagement-ranked highlights that overlap some segments. When a clip overlaps a ranked segment, it appears under an Overlapping clips: line on that match.

Use this for “find dialogue about a topic”. For “every line naming a person or company” use particle_podcast_find_mentions instead — person_slug and company_slug here narrow ranked results, they don’t drive the ranking.

What semantic_search is not good at:

Don’t ask it…	Use this instead
”Every line naming OpenAI” — a name, not a topic. Resolving the name and filtering finds the mentions; a vector query drifts to adjacent dialogue.	Resolve it, then particle_podcast_find_mentions with company_slug
An exact token that must appear verbatim — a ticker, model number, or drug name.	keyword_search (double-quote a phrase for an ordered match)

Crafting the query

semantic_search and keyword_search do different jobs. Most disappointing results come from using one where the other belongs.

semantic_search carries the idea. Write it as a sentence describing what should be discussed, in the words a speaker would actually use. It is paraphrase-tolerant, so it finds the topic however it happens to be phrased.

keyword_search carries words that must be literally spoken. Every word must appear in the same passage, so it is for one or two exact tokens — a ticker, a product name, a drug name — not for a description. A sentence here returns nothing, because no passage contains all of those words.

Use both when a topic must also contain an exact term. The result is their intersection, which is narrow by design. If it comes back empty, keyword_match: "ranked" relaxes the keyword side back to a relevance hint.

Goal	Call
Dialogue about a topic	semantic_search: "how AI is changing entry-level hiring"
A term that must be said	keyword_search: "QuillBot"
A topic that must name a term	semantic_search: "AI writing tools for students", keyword_search: "QuillBot"
An exact multi-word string	keyword_search: "\"founder mode\"" — quotes require adjacency, so keep them short
Several alternatives	One call per alternative. There is no boolean OR — a bare OR is a word that must be spoken
Everything said about a person	Resolve them, then particle_podcast_find_mentions

Never put a name in semantic_search. Resolve it with particle_person_resolve, particle_company_resolve, or particle_entity_resolve and pass the slug. Searching for "Sam Altman" as text finds passages that sound like him; person_slug: "sam-altman" finds the episodes actually featuring him.

Start broad, then narrow

Every filter compounds, and each one can remove all results on its own. Issue the query with semantic_search alone first, confirm the topic has coverage, then add filters.

If a search returns nothing because of your filters, the tool returns an error that names the specific parameter responsible and the corrected call to make — it is measured by re-running your query with each filter removed, not guessed. Act on it rather than re-issuing variations of the same query. When the query text genuinely matches nothing, you get an ordinary empty result instead, which is the signal to rephrase semantic_search.

role is the filter most likely to surprise: guest/host/panelist/ correspondent mean the person spoke in that specific capacity, speaker means they spoke in any of them, and mention means they were talked about rather than speaking. Omitting role covers speaking and mentions both, and is almost always what you want. These are the same values /v1/podcasts/episodes accepts.

Inputs

At least one of semantic_search or keyword_search is required.

Field	Type	Required	Default	Description
semantic_search	string	one of	—	Vector-similarity search by meaning. Express the query the way you’d describe the topic to a colleague — paraphrase tolerant. Combine with keyword_search for hybrid ranking. Describe a topic, not a name — for a specific person/company/entity filter with person_slug/company_slug/entity_slug (or use particle_podcast_find_mentions for every line about them); for an exact token use keyword_search.
keyword_search	string	one of	—	Words that must be literally spoken. Every word must appear in the same passage (see keyword_match), so keep it to the one or two words that must be said and put the rest of the idea in semantic_search. Double-quote a short string to also require adjacency. No boolean OR.
keyword_match	string	no	required	How unquoted keyword_search words are applied. required excludes any passage missing one of them, which also makes a hybrid call an intersection with semantic_search. ranked lets those words steer relevance without excluding anything — use it when keyword_search is a loose bag of related words that will not co-occur. Quoted phrases filter in both modes; to relax a phrase, remove its quotes rather than switching mode.
person_slug	string	no	—	Person slug from particle_person_resolve or particle_entity_resolve (e.g. "sam-altman"). Filters results to episodes featuring this person. Also accepts a bare entity slug for non-person entities like places. For “every line about X” use particle_podcast_find_mentions instead.
company_slug	string	no	—	Company slug, domain, or ID. Resolves to the company’s linked entity and applies as a filter.
entity_slug	string	no	—	Knowledge-graph entity slug from particle_entity_resolve for the long tail that isn’t a person or company — places, organizations, events, products, concepts (e.g. "germany"). Use person_slug for people and company_slug for companies.
entity_type	string	no	—	Narrow to dialogue in episodes that mention any entity of this category — e.g. book, company, movie, school. For “discussions of X that reference some book”. Ignored when a specific entity is named, which is strictly narrower. Categories come from particle_catalog.
podcast_slug	string	no	—	Podcast slug, internal ID, or numeric iTunes ID.
episode_slug	string	no	—	Filter to a specific episode by slug or ID.
segment_type	string	no	—	Segment type filter. One of: INTRO, PERSONAL_BANTER, TOPIC_DISCUSSION, INTERVIEW, TRANSITION, AD, OUTRO.
role	string	no	—	How the entity must relate to the episode. One of: guest, host, panelist, correspondent (spoke in that capacity), speaker (spoke in any of them, excluding mention-only episodes), or mention (talked about rather than speaking). Omit to match speaking and mentions both.
language	string	no	—	Restrict to episodes of podcasts in this language — ISO 639-1 code (e.g. "fr"). Matches the podcast’s primary language subtag, so fr covers fr-FR.
since	string	no	—	Only segments from episodes published on or after this ISO 8601 date.
until	string	no	—	Only segments from episodes published on or before this ISO 8601 date.
sort	string	no	relevance	Sort order. One of: relevance, recency.
context	integer (1–15)	no	1	Lines of surrounding dialogue around each matched line. Widens each match window in place — raise it instead of fetching the full transcript when a match needs more context.
limit	integer (1–50)	no	10	Results per page.
cursor	string	no	—	Opaque pagination cursor.

Output

A markdown document with ## Dialogue matches (N) and one ### Segment title section per match. Each section carries bulleted KV rows: - **Episode:**, - **Podcast:**, - **Podcast slug:**, - **Published:**, - **Episode slug:**, - **Segment type:**, - **Match:** (the source: semantic, keyword, or hybrid), then one or more bullets formatted Window @ start–end (or Preview @ … for truncated windows) followed by indented dialogue lines. Every line that matched the query is rendered with the entire Speaker: text wrapped in bold (a window can contain several matched lines); surrounding context renders as **Speaker:** text. When highlight clips overlap the segment, they appear under an Overlapping clips: line as bullets formatted Title (TYPE, score N) @ start–end — clip ID: <id>. When more pages exist, a horizontal rule and a **Cursor:** <value> line are appended.

Bolded lines mark the lines that ranked for the current query (a window can contain several). This is a different signal from the bolding in particle_podcast_find_mentions, where a bolded line means “this line names the resolved entity” — they answer different questions and can both be true within the same episode for different reasons.

Sample (semantic_search="how AI affects the labor market", limit=2):

## Dialogue matches (2)

### Labor Market Transformation from AI

- **Episode:** Where Investment Themes Intersect and Beat Markets
- **Podcast:** Thoughts on the Market
- **Podcast slug:** thoughts-on-the-market
- **Published:** 2026-04-20
- **Episode slug:** where-investment-themes-intersect-and-beat-markets
- **Segment type:** TOPIC_DISCUSSION
- **Match:** semantic
- Window @ 108s–143s
    **Stephen Byrd: Now, at the same time, AI is reshaping the labor market.**
    **Stephen Byrd:** And on net, we see a four percent job loss driven by eleven percent of outright elimination…

### Goldman Sachs Report on AI and Job Displacement

- **Episode:** TNB Tech Minute: Thrive Capital and Andreesen Horowitz Co-lead …
- **Podcast:** WSJ Tech News Briefing
- **Podcast slug:** wsj-tech-news-briefing
- **Published:** 2026-03-03
- **Episode slug:** tnb-tech-minute-thrive-capital-and-andreesen-horowitz-co-lead-multibillion
- **Segment type:** TOPIC_DISCUSSION
- **Match:** semantic
- Window @ 43s–67s
    **Danny Lewis: Speaking of AI, a new research report by Goldman Sachs is predicting the technology will eventually displace eleven million jobs…**

Overlapping clips:
- AI to displace 11 million jobs (SHOCKING, score 84) @ 40s–72s — clip ID: e8342676-…
---

**Cursor:** r.4gfFC6

The string after - **Episode slug:** is what you can feed into particle_podcast_get_episode for the full transcript or clip list, or into particle_podcast_find_mentions (format=detail, episode_slug) for mention windows around a specific person.

Example

Agent calls: particle_podcast_search_transcripts {
  "semantic_search": "how AI affects the labor market",
  "podcast_slug": "all-in",
  "since": "2024-01-01",
  "context": 4,
  "limit": 5
}

For hybrid ranking, populate both semantic_search and keyword_search:

Agent calls: particle_podcast_search_transcripts {
  "semantic_search": "what investors think of GPT-5",
  "keyword_search": "GPT-5",
  "limit": 10
}

Related

• REST equivalent: GET /v1/podcasts/episodes/search.
• For “every line naming X” use particle_podcast_find_mentions.
• For a known episode’s full clip list, use particle_podcast_get_episode with include: ["clips"].
• For metadata-only episode discovery (no dialogue), use particle_podcast_list_episodes.