{ "openapi": "3.0.1", "info": { "title": "Youtube Transcript Scraper", "description": "Lightning-fast transcript extraction with pay-per-result pricing.\n\nExtract comprehensive transcript data from YouTube videos using official APIs. Get paragraph-formatted transcript text, timed segments, and metadata with 15 complete fields in just 1-2 seconds per video.", "version": "2.5", "x-build-id": "e8nWZCZg5G0GIo3aX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/coregent~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-coregent-youtube-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/coregent~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-coregent-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/coregent~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-coregent-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "videoRefs": { "title": "Video URLs or IDs", "type": "array", "description": "Specific videos to scrape. Accepts video URLs (watch or youtu.be) or raw 11-char video IDs. Only the videos you list here are scraped — one transcript per video. To scrape whole channels, playlists, or a seed video's channel, use the \"Discovery Sources\" input below instead.", "items": { "type": "string" }, "default": [] }, "channelPlaylistRefs": { "title": "Discovery Sources", "type": "array", "description": "Sources to discover videos from. Accepts four kinds of entries: (1) channel URLs (youtube.com/@handle, /channel/UC..., /c/..., /user/...), (2) playlist URLs (...?list=...), (3) seed video URLs/IDs, and (4) plain search keywords (e.g. \"ai automation tutorial\"). Channels and playlists expand into their videos; a seed video is resolved to its owning channel and that channel's videos are scraped (not just the seed video); a search keyword returns the top matching videos from YouTube search. A video URL here scrapes its whole channel — to scrape only a specific video, use the \"Video URLs or IDs\" input above instead. Each source is capped by \"Max videos per source\". ⚠️ Search keywords are NOT affected by the Published after/before date filters and are always returned in YouTube's relevance order (ordering is not configurable); the date filters apply only to channels, playlists, and seed videos.", "items": { "type": "string" }, "default": [] }, "maxVideosPerSource": { "title": "Max videos per source", "minimum": 1, "type": "integer", "description": "Cap how many videos to take from each discovery source (channel, playlist, seed-video-derived channel, or search keyword). Does not affect videos listed in the \"Video URLs or IDs\" input.", "default": 50 }, "startDate": { "title": "Published after (optional)", "type": "string", "description": "ISO date (YYYY-MM-DD). For channel, playlist, and seed-video expansion, only include videos published on or after this date. Does not apply to search-keyword sources. Leave empty for no lower bound.", "default": "" }, "endDate": { "title": "Published before (optional)", "type": "string", "description": "ISO date (YYYY-MM-DD). For channel, playlist, and seed-video expansion, only include videos published on or before this date. Does not apply to search-keyword sources. Leave empty for no upper bound.", "default": "" }, "language": { "title": "Transcript language", "enum": [ "", "en", "es", "de", "fr", "pt", "ja", "hi", "zh", "ko", "ru", "ar", "bn", "ta", "te", "mr", "gu", "kn", "ml", "ur", "pa", "th", "vi", "id", "tr", "it", "nl", "pl", "uk", "ro", "cs", "sv", "da", "fi", "no" ], "type": "string", "description": "Language of the transcript to return. Leave on \"Auto-detect\" to return each video's original transcript language. Choosing a specific language returns that caption track when the video has it, otherwise falls back to the video's original transcript.", "default": "" }, "subtitleFormats": { "title": "Subtitle formats", "enum": [ "both", "srt", "vtt", "none" ], "type": "string", "description": "Which ready-to-use subtitle strings to include in each record (generated locally from the timed segments — no extra API cost). \"SRT + VTT\" is the default; pick one to slim the output, or \"None\" to omit both. The unselected field is set to null — the srt/vtt fields always exist so every record keeps the same shape.", "default": "both" }, "maxResults": { "title": "Max videos total (optional)", "minimum": 0, "type": "integer", "description": "Cap the total number of videos processed this run, across both inputs (after channel/playlist expansion). 0 = no cap.", "default": 0 } } }, "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 } } }, "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 } } } } } } } } } }