{ "openapi": "3.0.1", "info": { "title": "Podcast Transcript & Episode Scraper - From RSS, No Audio", "description": "Get podcast episodes with the transcripts publishers make public: reads RSS podcast:transcript files (SRT, VTT, JSON, HTML), transcript links in show notes, chapters, guests, sponsors and links. Search keywords across episodes. Not speech-to-text, no API key.", "version": "2.0", "x-build-id": "4lPOdzbrHoDq4ANHx" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/that_red_bird~podcast-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-that_red_bird-podcast-transcript-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/that_red_bird~podcast-transcript-scraper/runs": { "post": { "operationId": "runs-sync-that_red_bird-podcast-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/that_red_bird~podcast-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-that_red_bird-podcast-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "feeds": { "title": "Podcasts", "type": "array", "description": "Podcast RSS feed URLs, Apple Podcasts links (podcasts.apple.com/.../id123456789) or plain show names (the best Apple Podcasts search match is used). The defaults are two shows that publish transcripts (Podcasting 2.0 and Acquired).", "default": [ "https://feeds.podcastindex.org/pc20.xml", "https://feeds.transistor.fm/acquired" ], "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Max episodes per podcast", "minimum": 1, "maximum": 2000, "type": "integer", "description": "How many episodes to return per podcast (newest first). Each returned episode is one billable result.", "default": 5 }, "keywords": { "title": "Search keywords across episodes", "type": "array", "description": "Optional. Only episodes whose title, show notes or published transcript contain one of these words/phrases are returned, with context snippets (and the time in the episode when the transcript has timestamps). Case-insensitive.", "default": [], "items": { "type": "string" } }, "maxEpisodesToScan": { "title": "Episodes checked when searching", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Only used with keywords: how many of the newest episodes per podcast are checked (transcripts are downloaded for each) before the matching ones are returned.", "default": 50 }, "since": { "title": "Only episodes after", "type": "string", "description": "ISO date, e.g. 2026-01-01. Older episodes are skipped. Leave empty for no limit.", "default": "" }, "minDurationMinutes": { "title": "Minimum duration (minutes)", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Skip shorter episodes such as trailers. 0 = no minimum.", "default": 0 }, "onlyEpisodesWithTranscript": { "title": "Only episodes that have a transcript", "type": "boolean", "description": "Skip episodes without a published transcript. Useful to build a transcript corpus from mixed feeds.", "default": false }, "fetchTranscripts": { "title": "Download transcripts", "type": "boolean", "description": "Download the transcript files that the feed lists (podcast:transcript tags) and turn them into text. Off = only report where a transcript is available.", "default": true }, "followTranscriptLinks": { "title": "Follow transcript links in show notes", "type": "boolean", "description": "When the feed has no transcript tag but the show notes link to a page named 'transcript', fetch that page and use its text if it is long enough to be a transcript.", "default": true }, "includeTranscriptText": { "title": "Include transcript text", "type": "boolean", "description": "Put the full transcript text in each episode row. Turn off to get only status, URL and word count.", "default": true }, "includeTranscriptSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Also output the transcript as segments with start time, end time and speaker (when the file has them). Makes rows larger.", "default": false }, "maxTranscriptChars": { "title": "Max transcript length (characters)", "minimum": 1000, "maximum": 5000000, "type": "integer", "description": "Longer transcripts are cut at this length in the output (transcriptTruncated is then true). Keyword search still reads the full transcript.", "default": 200000 }, "fetchChapters": { "title": "Fetch chapter files", "type": "boolean", "description": "Download podcast:chapters JSON files. Timestamp lists written in the show notes are used as chapters when no chapter file exists.", "default": true }, "includeShowNotes": { "title": "Include show notes", "type": "boolean", "description": "Include the episode description as plain text (first 8,000 characters). Links and sponsor mentions are extracted either way.", "default": true }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many podcasts to process in parallel.", "default": 3 } } }, "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 } } } } } } } } } }