Firecrawl Alexandria

Particle

1Request
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.

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.

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.

number

Lines of surrounding dialogue around each matched line. Widen this instead of fetching the transcript.

number

Maximum records to return.

15 credits
Codefollows the fields above
const result = await firecrawl.scrape({
  alexandria: {
    provider: "particle",
    capability: "podcasts/episodes/search",
    options: {
      keyword_match: "required",
      context: 1,
      limit: 25,
    },
  },
});
2Response example

This is a sample shape. Press Run to see live data from Particle.

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