Listen to Sadhu

• author_list — List all authors.
• author_resolve — Find a author by name (fuzzy).
• document_get — Get a document (commentary/prose_chapter/letter) by id.
• document_list — List documents at a reference / in a book. A verse's purport = document_list(source, tokens, kind:"commentary").
• excerpt_prepare — Generate (or fetch, if cached) the audio clip for a lecture passage and return its playable URL. This is the excerpt player's Play action — it is called for you
• excerpt_render — Let the user HEAR a lecture passage inline. Call this when the user wants to LISTEN to a specific moment in a track — e.g. from a search(types:["track"]) hit, p
• location_list — List all locations.
• location_resolve — Find a location by name (fuzzy).
• media_render — Show/play an existing corpus VIDEO clip inline. Call this when the user wants to WATCH a clip found via search(types:["media"]) — pass the hit's media_id. Rende
• search — Semantic + lexical search over the corpus. Returns verses, documents, track passages and titles matching a natural-language query, each with the id needed to fe
• source_get — Get one book by id or code ("source_…" or "BG"/"БГ").
• source_list — List all books (Caitanya-caritāmṛta is three sources).
• source_resolve — Find a book by name (fuzzy): "gita", "бхагаватам", "CC Madhya".
• track_get — Get a track (lecture/conversation): metadata, cited references, transcript/pdf availability.
• track_list — List tracks, filterable by reference (source[+tokens] = tracks citing it), author/location/kind/date/lang. No filter ⇒ recent tracks (date desc).
• transcript_window — Read a track's transcript around a time window (from a search track hit or track_list). Widen with pad_ms.

No long description beyond the summary.