# Particle · Episode search

Find companies, people and contact details with Particle · Episode search from Alexandria through one Spiral API key. Use to find episodes that discussed something. 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. It runs in the background and returns structured JSON. Pay as you go, with no subscription.

- Provider: Alexandria
- Category: Lead Gen
- Runs: In the background
- Returns: json
- Tool id: `alexandria` / `particle/podcasts/episodes/search`
- Page: https://spiral.ai/tools/alexandria/particle/podcasts/episodes/search

## Pricing

$0.026189 per call.

## Limits

- Longest queue wait: 1 hour
- Run deadline: 5 minutes
- Longest run, end to end: 225 minutes
- Largest inline input: 1 MB
- Largest input file: 2 GB
- Largest output: 5 GB

## Input

| Field | Kind | Allowed | Default | Description |
| --- | --- | --- | --- | --- |
| `role` | one of | guest, host, panelist, correspondent, speaker, mention | — | How the entity must relate to the episode: a speaking role, speaker for any speaking role, or mention for being talked about. |
| `sort` | one of | relevance, recency | — | relevance (default) or recency. |
| `type` | one of | INTRO, PERSONAL_BANTER, TOPIC_DISCUSSION, INTERVIEW, TRANSITION, AD, OUTRO | — | Only segments of this type. |
| `limit` | number | 1 to 100 | 25 | Maximum records to return. |
| `since` | text |  | — | Only segments from episodes published after this date. |
| `until` | text |  | — | Only segments from episodes published on or before this date. A bare date covers the whole day. |
| `cursor` | text |  | — | Opaque cursor from a previous page. Omit for the first page; send the same filters with it. |
| `context` | number | 1 to 15 | 1 | Lines of surrounding dialogue around each matched line. Widen this instead of fetching the transcript. |
| `language` | text |  | — | ISO 639-1 language code, for example en or fr. Matches the primary subtag, so fr covers fr-CA. |
| `entity_id` | text |  | — | Restrict to episodes featuring this entity, by slug or id. Ranking still comes from the search terms. |
| `company_id` | text |  | — | Restrict to episodes featuring this company, by slug, domain or id. |
| `episode_id` | text |  | — | Restrict to one episode, by slug or id. |
| `podcast_id` | text |  | — | Restrict to one show, by slug, id or Apple collection id. |
| `entity_type` | text |  | — | Restrict to episodes that mention any entity of this category slug (company, school, book). Not combinable with role. |
| `keyword_match` | one of | required, ranked | required | 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. |
| `keyword_search` | text |  | — | 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. |
| `semantic_search` | text |  | — | 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

```bash
curl https://api.spiral.ai/v1/runs \
  -H "Authorization: Bearer $SPIRAL_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: $(uuidgen)" \
  -d '{
    "provider": "alexandria",
    "model": "particle/podcasts/episodes/search",
    "input": {
      "semantic_search": "<semantic_search>"
    }
  }'
```

Try it in the Playground: https://spiral.ai/start?provider=alexandria&model=particle%2Fpodcasts%2Fepisodes%2Fsearch

## Common questions

### Particle · Episode search

**How much does Particle · Episode search cost?**

$0.026189 per call. You pay as you go from one Spiral balance, with no subscription, and a failed run is not charged.

**How do I use Particle · Episode search through an API?**

Send `POST /v1/runs` with `"provider": "alexandria"`, `"model": "particle/podcasts/episodes/search"` and the input fields on this page, using one Spiral API key. It runs in the background: poll the run, or name a webhook to be told when it finishes.

**Do I need an account with Alexandria to use Particle · Episode search?**

No. Spiral runs it on its own Alexandria account and charges your Spiral balance.

**Can my AI agent use Particle · Episode search?**

Yes. Agents find and run it through Spiral's MCP server, CLI or agent skill, with the same API key.

