> ## Documentation Index > Fetch the complete documentation index at: https://docs.particle.pro/llms.txt > Use this file to discover all available pages before exploring further. # Related Podcasts > Shows related to a given show — ranked by content, topics, shared guests, network and sponsors — with the reasons attached. Given one show, which other shows are like it? Particle API answers with a ranked, explainable list computed from what is actually in the audio and the metadata around it: the content of recent episodes (embedded transcripts), the show's topic profile, the guests it books, the network it belongs to, and the advertisers it carries. Every result carries a calibrated score, a coarse band, and — on request — the specific signals that make the pair related, so a client can tell "same beat, same audience" from "same network, different subject" instead of trusting a bare number. Related sets are precomputed per show and refreshed as new episodes arrive, so the endpoint is a fast page read rather than a live search. ## List related podcasts ```bash theme={"dark"} curl -s -H "X-API-Key: $PARTICLE_API_KEY" \ "https://api.particle.pro/v1/podcasts/all-in/related?include=basis&limit=3" ``` ```json Response (truncated) theme={"dark"} { "data": [ { "podcast": { "id": "4oGfeKqQ8zUwbF1Wm2u3yh", "title": "This Week in Startups", "slug": "this-week-in-startups", "publisher": { "id": "…", "name": "…", "slug": "…" } }, "score": 0.91, "band": "strong", "basis": { "content_similarity": 0.84, "topic_overlap": 0.71, "shared_topics": [ { "id": "…", "name": "Venture Capital", "slug": "business/venture-capital" } ], "shared_guest_count": 9, "shared_guests": [ { "id": "…", "name": "…", "slug": "…" } ], "same_publisher": false, "shared_sponsor_count": 3, "shared_category_count": 2 } } ], "has_more": true, "cursor": "r.…" } ``` | Parameter | Meaning | | ----------------- | ----------------------------------------------------------------------------------------------------------------------------------------- | | `id` (path) | Podcast slug, internal ID, or numeric iTunes ID — the same identifiers every podcast endpoint accepts. | | `include` | `basis` attaches the explanation object to every result. Omit it for the lean form (podcast, score, band). | | `min_score` | Drop results below this fused score. Prefer filtering on `band`; the score's exact thresholds may be recalibrated as the ranker improves. | | `limit`, `cursor` | Standard pagination over the stored ranking (up to 50 related shows per podcast; `limit` defaults to 25, max 100). | ## The five most related shows inline The podcast detail embeds the lean form on request, so one call answers "what else is like this" without a second round trip. The same `include` parameter also takes `recommended_guests` (the five guests the show could book next) and `recommended_sponsors` (premium-grade; the five advertisers active on shows like this one that do not buy it yet), the inline forms of [`/recommendations/guests`](/podcasts/guests#recommended-guests-for-a-podcast) and [`/recommendations/sponsors`](/podcasts/advertising#sponsors-a-podcast-could-pitch): ```bash theme={"dark"} curl -s -H "X-API-Key: $PARTICLE_API_KEY" \ "https://api.particle.pro/v1/podcasts/all-in?include=related" ``` ```json Response (truncated) theme={"dark"} { "id": "…", "title": "All-In with Chamath, Jason, Sacks & Friedberg", "slug": "all-in", "related": [ { "podcast": { "id": "…", "title": "This Week in Startups", "slug": "this-week-in-startups" }, "score": 0.91, "band": "strong" }, { "podcast": { "id": "…", "title": "The Twenty Minute VC", "slug": "the-twenty-minute-vc" }, "score": 0.87, "band": "strong" } ] } ``` `related` is omitted when the show's set has not been computed yet. The full list, pagination, and the `basis` live on `GET /v1/podcasts/{id}/related`. ## Reading a result | Field | Meaning | | -------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `score` | Fused relatedness in (0, 1], calibrated so that higher values are more likely to be judged related by an editor. Comparable across shows. | | `band` | `strong` (same beat and audience), `moderate` (overlapping subject or audience but a different beat), `weak` (a loose connection). Branch on this rather than on raw score thresholds. | | `basis.content_similarity` | Cosine similarity between the two shows' content centroids, each derived from recent episode transcripts. Omitted when either show has too few embedded episodes — an absent signal, not a low one. | | `basis.topic_overlap` / `basis.shared_topics` | Overlap of the two shows' topic profiles, and up to three topics that contribute most to it. Topic slugs are valid `topic_id` values on `GET /v1/podcasts`. | | `basis.shared_guest_count` / `basis.shared_guests` | Guests who appeared on both shows; up to three are named, most significant first. Circuit regulars who appear everywhere are discounted. Person slugs feed `GET /v1/podcasts/guests/{id}`. | | `basis.same_publisher` | Both shows belong to the same multi-show publisher (network). Singleton publishers carry no signal. | | `basis.shared_sponsor_count` | Advertisers both shows have carried. | | `basis.shared_category_count` | Directory categories the shows share. | Related shows are restricted to the source show's language, and a show's own list never contains itself. A show whose related set has not been computed yet returns `200` with an empty `data` array, not `404` — the show exists; its relatedness simply has not landed. ## MCP The same data is available to agents as [`particle_podcast_list_related`](/mcp/tools/podcasts/podcast-list-related) (with `include: ["basis"]`), and inline on [`particle_podcast_resolve`](/mcp/tools/podcasts/podcast-resolve) via `include: ["related"]`. ## Choosing the right endpoint | You want… | Use | | ---------------------------------------- | -------------------------------------------- | | Shows like this show | `GET /v1/podcasts/{id}/related` (this page) | | Shows that discuss a topic | `GET /v1/podcasts?topic_id=…` | | Shows a specific guest has appeared on | `GET /v1/podcasts/guests/{id}/podcasts` | | Advertisers that co-occur with a sponsor | `GET /v1/podcasts/advertising/co-occurrence` | | Where a phrase or idea is discussed | `GET /v1/podcasts/episodes/search` | ## How it is computed For each show, candidates come from five independent arms — nearest shows by content centroid, shows sharing a guest, shows concentrated in its most specific topics, the show's own publisher, and shows sharing a sponsor — and every candidate is scored on all signals at once, so a show with no embedded episodes still gets neighbours from its guests, topics and network. Sets are recomputed when new episodes land, coalesced so a daily show recomputes a few times a day rather than once per episode. The ranker was validated against an external listener-behaviour reference (Apple's "You Might Also Like" lists), a temporal shared-guest holdout, and a calibrated editorial judge; the methodology and the measured recall and precision figures are published with the [changelog entry](/changelog) for this endpoint once the full-catalogue evaluation completes.