# Particle · Episode counts over time

Find companies, people and contact details with Particle · Episode counts over time from Alexandria through one Spiral API key. Use for a trend rather than a list: how often a person appeared by month, how a show's output changed, how many episodes discussed a term each week. One call replaces paging the episode list per period. 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/timeseries`
- Page: https://spiral.ai/tools/alexandria/particle/podcasts/episodes/timeseries

## Pricing

$0.00873 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. |
| `interval` | one of | day, week, month | week | Bucket width. Weeks start on Monday; all buckets are UTC-aligned. |
| `language` | text |  | — | ISO 639-1 language code, for example en or fr. Matches the primary subtag, so fr covers fr-CA. |
| `entity_id` | text |  | — | Episodes featuring this entity as a speaker or a mention, by slug (elon-musk, openai) or id. |
| `person_id` | text |  | — | Episodes where this person speaks, by person slug, entity slug or id. Works when the speaker has no knowledge-graph entity. |
| `company_id` | text |  | — | Episodes featuring this company, by slug, domain or id. |
| `podcast_id` | text |  | — | Restrict to one show, by slug, id or Apple collection id. |
| `max_duration` | number | 0 to 9223372036 | — | Maximum length in seconds. |
| `min_duration` | number | 0 to 9223372036 | — | Minimum length in seconds. |
| `fully_ingested` | true or false |  | — | Only episodes that reached the terminal ingestion milestone. |
| `has_transcript` | true or false |  | — | Only episodes with a completed transcript. |
| `keyword_search` | text |  | — | Count episodes whose transcripts contain these terms (quoted phrases exact). Adds per-bucket mention_count. Not combinable with semantic_search. |
| `published_after` | text |  | — | Only episodes published after this ISO 8601 date or date-time. |
| `semantic_search` | text |  | — | Count episodes whose transcripts match this meaning, at the search endpoint's threshold. Requires published_after. Not combinable with keyword_search. |
| `published_before` | text |  | — | Only episodes published before this ISO 8601 date or date-time. |

## 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/timeseries",
    "input": {
      "entity_id": "<entity_id>"
    }
  }'
```

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

## Common questions

### Particle · Episode counts over time

**How much does Particle · Episode counts over time cost?**

$0.00873 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 counts over time through an API?**

Send `POST /v1/runs` with `"provider": "alexandria"`, `"model": "particle/podcasts/episodes/timeseries"` 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 counts over time?**

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

**Can my AI agent use Particle · Episode counts over time?**

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

