---
type: "firecrawl-provider"
description: "Matching transcript segments with compact episode records under data. Beside data the body carries the resolved entity or company block when one was passed, and a diagnostics block when nothing matched. Read episode.id and fetch podcasts/episode for the optional episode web URL or audio stream; search does not return those links."
use_when: "Use to find podcast episodes and conversations that discussed a topic, such as podcast conversations about AI agents, by searching what was said in the transcripts. This is the entry point: it returns ids the other podcast capabilities take. For every line about one person or company use podcasts/mentions instead."
credits_per_call: 15
options: 17
---
# Particle: Episode search

Matching transcript segments with compact episode records under data. Beside data the body carries the resolved entity or company block when one was passed, and a diagnostics block when nothing matched. Read episode.id and fetch podcasts/episode for the optional episode web URL or audio stream; search does not return those links.

## Agent instructions

Use to find podcast episodes and conversations that discussed a topic, such as podcast conversations about AI agents, by searching what was said in the transcripts. This is the entry point: it returns ids the other podcast capabilities take. For every line about one person or company use podcasts/mentions instead.

- Category file: [Podcasts category](https://alexandria.firecrawl.dev/agents/categories/podcasts)
- Provider file: [Provider guide](https://alexandria.firecrawl.dev/agents/providers/particle)
- Provider key: `particle`
- Capability: `podcasts/episodes/search`
- Cost: 15 credits per call

## Request options

- `semantic_search` (string): What was talked about, in your own words. Paraphrase-tolerant, so it finds dialogue that means this without containing these exact words. Describe a topic, not a name: for a person or company use entity_id or podcasts/mentions. Example: `<semantic_search>`
- `keyword_search` (string): Exact tokens or phrases to match in the transcript, ranked BM25. Use for tickers, drug names, product codes. Wrap a phrase in double quotes to require it contiguously. Example: `<keyword_search>`
- `keyword_match` (string): How unquoted keyword terms apply: required filters to segments containing every term (and constrains a hybrid query to their intersection); ranked lets them only boost. Example: `required`
- `entity_id` (string): Restrict to episodes featuring this entity, by slug or id. Ranking still comes from the search terms. Example: `<entity_id>`
- `entity_type` (string): Restrict to episodes that mention any entity of this category slug (company, school, book). Not combinable with role. Example: `<entity_type>`
- `company_id` (string): Restrict to episodes featuring this company, by slug, domain or id. Example: `<company_id>`
- `episode_id` (string): Restrict to one episode, by slug or id. Example: `<episode_id>`
- `podcast_id` (string): Restrict to one show, by slug, id or Apple collection id. Example: `<podcast_id>`
- `type` (string): Only segments of this type. Example: `INTRO`
- `role` (string): How the entity must relate to the episode: a speaking role, speaker for any speaking role, or mention for being talked about. Example: `guest`
- `language` (string): ISO 639-1 language code, for example en or fr. Matches the primary subtag, so fr covers fr-CA. Example: `<language>`
- `since` (string): Only segments from episodes published after this date. Example: `<since>`
- `until` (string): Only segments from episodes published on or before this date. A bare date covers the whole day. Example: `<until>`
- `sort` (string): relevance (default) or recency. Example: `relevance`
- `context` (number): Lines of surrounding dialogue around each matched line. Widen this instead of fetching the transcript. Example: `1`
- `limit` (number): Maximum records to return. Example: `25`
- `cursor` (string): Opaque cursor from a previous page. Omit for the first page; send the same filters with it. Example: `<cursor>`

## Request shape

Call `POST https://api.firecrawl.dev/v2/scrape` with `{ alexandria: <request> }` and your Firecrawl API key.

```json
{
  "provider": "particle",
  "capability": "podcasts/episodes/search",
  "options": {
    "semantic_search": "<semantic_search>",
    "keyword_match": "required",
    "context": 1,
    "limit": 25
  }
}
```

### JavaScript

```javascript
const result = await firecrawl.scrape({
  alexandria: {
    provider: "particle",
    capability: "podcasts/episodes/search",
    options: {
      semantic_search: "<semantic_search>",
      keyword_match: "required",
      context: 1,
      limit: 25,
    },
  },
});
```

### Python

```python
result = firecrawl.scrape_alexandria({
  "provider": "particle",
  "capability": "podcasts/episodes/search",
  "options": {
    "semantic_search": "<semantic_search>",
    "keyword_match": "required",
    "context": 1,
    "limit": 25
  }
})
```

### cURL

```sh
curl https://api.firecrawl.dev/v2/scrape \
  -H "Authorization: Bearer $FIRECRAWL_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "alexandria": {
    "provider": "particle",
    "capability": "podcasts/episodes/search",
    "options": {
      "semantic_search": "<semantic_search>",
      "keyword_match": "required",
      "context": 1,
      "limit": 25
    }
  }
}'
```

### CLI

```sh
firecrawl scrape 'particle/podcasts/episodes/search' \
  --options '{"semantic_search":"<semantic_search>","keyword_match":"required","context":1,"limit":25}'
```


## Response data

The response includes `success`, `provider`, `capability`, `creditsCost` and `data`. These fields and the example below describe the provider payload in `data`.

```json
{
  "data": [
    {
      "episode": {},
      "segment": {},
      "windows": [],
      "match": {},
      "clips": []
    }
  ]
}
```

## Explore other popular capabilities

If this capability is not the best match, fetch only the relevant capability file:

- [Show search](https://alexandria.firecrawl.dev/agents/providers/particle/podcasts/search): Matching shows, each with a match_quality from exact down to speculative, and the same filters podcasts/list takes.
- [Show directory](https://alexandria.firecrawl.dev/agents/providers/particle/podcasts/list): Shows matching the filters, most popular first when no query is given.
- [Show lookup by platform id](https://alexandria.firecrawl.dev/agents/providers/particle/podcasts/lookup): One result per identifier passed, echoing it beside the matched podcast. An unresolved identifier has no podcast field.
- [Podcast episode](https://alexandria.firecrawl.dev/agents/providers/particle/podcasts/episode): One episode, returned directly: its show, publication date, duration, speakers, topics, and optional web and audio links.
- [Episode transcript](https://alexandria.firecrawl.dev/agents/providers/particle/podcasts/transcript): In the dialogue format: the full transcript as ordered, numbered, speaker-labelled lines under lines, with episode_id, language and duration_seconds beside them. The text and srt formats answer with that format's body instead.