{ "openapi": "3.0.1", "info": { "title": "Podcast RSS Scraper & Transcriber", "description": "Scrape any podcast RSS feed for episodes with metadata, durations and chapters. Get FREE publisher transcripts (Podcasting 2.0) or fall back to Whisper with your own key. Bulk-import subscriptions via OPML, filter by date/duration/title, and monitor shows for new episodes.", "version": "0.6", "x-build-id": "RTqAjChybF5aXSeoS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/celebrated-quadraphonic~podcast-rss-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-celebrated-quadraphonic-podcast-rss-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/celebrated-quadraphonic~podcast-rss-scraper/runs": { "post": { "operationId": "runs-sync-celebrated-quadraphonic-podcast-rss-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/celebrated-quadraphonic~podcast-rss-scraper/run-sync": { "post": { "operationId": "run-sync-celebrated-quadraphonic-podcast-rss-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "country": { "title": "iTunes store country", "type": "string", "description": "Two-letter iTunes Store country code used for search (e.g. US, GB, DE, JP). Affects which shows Apple returns.", "default": "US" }, "feedUrls": { "title": "RSS feed URLs", "type": "array", "description": "Direct podcast RSS feed URLs, one per line. Example: https://feeds.npr.org/510318/podcast.xml", "items": { "type": "string" } }, "opmlUrls": { "title": "OPML URLs / XML", "type": "array", "description": "OPML subscription lists to bulk-import podcast feeds: paste OPML URLs or raw OPML XML, one per line. Great for monitoring many shows at once.", "items": { "type": "string" } }, "maxAudioMinutes": { "title": "Max audio minutes per episode", "minimum": 1, "maximum": 120, "type": "integer", "description": "Only the first N minutes of each episode's audio are sent to Whisper (also capped by the 25 MB upload limit).", "default": 30 }, "maxDurationSeconds": { "title": "Max duration (seconds)", "minimum": 0, "type": "integer", "description": "Skip episodes longer than this. 0 = no maximum.", "default": 0 }, "maxEpisodesPerFeed": { "title": "Max episodes per feed", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many of each feed's newest episodes to scrape.", "default": 20 }, "maxResultsPerSearch": { "title": "Max results per search", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum podcast shows resolved per search term (iTunes limit: 200).", "default": 5 }, "maxTranscribeEpisodes": { "title": "Max episodes to transcribe", "minimum": 1, "maximum": 100, "type": "integer", "description": "Safety cap on how many episodes Whisper transcribes per run (publisher transcripts are always free and unlimited).", "default": 3 }, "minDurationSeconds": { "title": "Min duration (seconds)", "minimum": 0, "type": "integer", "description": "Skip episodes shorter than this. Useful to exclude trailers and teasers. 0 = no minimum.", "default": 0 }, "newEpisodesOnly": { "title": "Monitor mode: new episodes only", "type": "boolean", "description": "Output only episodes not seen in previous runs (state is kept in the run's key-value store). Ideal for scheduled monitoring of shows.", "default": false }, "openaiApiKey": { "title": "OpenAI API key", "type": "string", "description": "Your OpenAI API key, used only when Whisper transcription is enabled. Stored securely as a secret." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. RSS feeds and the iTunes API have no anti-bot protection, so proxies are not needed.", "default": { "useApifyProxy": false } }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Only episodes published on or after this date. Format: YYYY-MM-DD (e.g. 2025-01-01). Leave empty for no lower bound.", "default": "" }, "publishedBefore": { "title": "Published before", "type": "string", "description": "Only episodes published on or before this date. Format: YYYY-MM-DD. Leave empty for no upper bound.", "default": "" }, "requestConcurrency": { "title": "Request concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many feeds / transcripts to fetch in parallel. Pure HTTP, no browser or proxy needed.", "default": 5 }, "searchTerms": { "title": "Search terms (Apple Podcasts)", "type": "array", "description": "Keywords to discover podcasts via the Apple Podcasts (iTunes) Search API. Each term resolves to matching show feeds.", "items": { "type": "string" } }, "titleContains": { "title": "Title contains", "type": "string", "description": "Case-insensitive keyword filter on episode titles. Separate alternatives with |, e.g. interview|founder. Leave empty to keep all episodes.", "default": "" }, "transcribe": { "title": "Transcribe with Whisper (fallback)", "type": "boolean", "description": "Transcribe episode audio via the OpenAI Whisper API for episodes that have no free publisher transcript. Requires your own OpenAI API key; you pay OpenAI directly.", "default": false }, "usePublisherTranscripts": { "title": "Use free publisher transcripts", "type": "boolean", "description": "Fetch free transcripts published by the show itself via the Podcasting 2.0 tag. No API key and no transcription cost. Falls back to Whisper only when enabled below.", "default": true }, "transcriptFormats": { "title": "Transcript output formats", "type": "array", "description": "Which transcript formats to include per episode, one per line: text, srt, vtt. Defaults to text + srt. If a found transcript cannot provide a requested format, plain text is kept as fallback (transcriptStatus = format_fallback).", "items": { "type": "string" } }, "transcriptLanguage": { "title": "Transcript language hint", "type": "string", "description": "ISO-639-1 language code (e.g. en, es, de) passed to Whisper as a hint for faster, more accurate transcription. Leave empty for auto-detect." }, "whisperModel": { "title": "Whisper model", "enum": [ "whisper-1", "gpt-4o-transcribe", "gpt-4o-mini-transcribe" ], "type": "string", "description": "OpenAI speech-to-text model used for transcription.", "default": "whisper-1" } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }