{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper", "description": "Extract YouTube transcripts with millisecond timestamps. Give it a video, a channel, a playlist or a search keyword and get raw caption segments plus merged paragraphs, ready for RAG, search and analysis. Incremental mode skips videos you already have, so a scheduled run does not bill you twice.", "version": "0.1", "x-build-id": "h8jca49PnKsCap6uz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/garnet_puppet~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-garnet_puppet-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/garnet_puppet~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-garnet_puppet-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/garnet_puppet~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-garnet_puppet-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "YouTube URLs", "type": "array", "description": "Any mix of YouTube links. Video and Shorts links are scraped directly; channel and playlist links are expanded into their videos automatically.", "items": { "type": "string" } }, "searchKeywords": { "title": "Search keywords", "type": "array", "description": "Search YouTube for each keyword and scrape transcripts from the top results. No video URL needed.", "default": [], "items": { "type": "string" } }, "previewOnly": { "title": "Preview only (no transcript charges)", "type": "boolean", "description": "List which videos would be scraped and how many would be charged, without fetching any transcript. Only the actor start event is billed; no transcript charges are made.", "default": false }, "outputFormat": { "title": "Transcript format", "enum": [ "json", "text", "srt", "vtt" ], "type": "string", "description": "Adds a ready-to-use transcript string to each record. Timestamps, segments and paragraphs are always included as well.", "default": "json" }, "scrapeShorts": { "title": "Include Shorts", "type": "boolean", "description": "When expanding a channel, also include Shorts, added after regular videos. Max videos per source applies to the combined list, so a low limit may leave no room for Shorts. Shorts links given directly are always scraped.", "default": false }, "chunkBy": { "title": "Paragraph boundaries", "enum": [ "time", "chapter" ], "type": "string", "description": "Chapter mode splits paragraphs on the video's own chapters when it has them, and falls back to fixed length otherwise.", "default": "time" }, "maxVideosPerSource": { "title": "Max videos per source", "minimum": 1, "maximum": 200, "type": "integer", "description": "Upper limit of videos taken from each channel, playlist or search. Defaults to 30." }, "maxPagesPerSource": { "title": "Max pages per source", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many result pages to fetch from each channel, playlist or search.", "default": 10 }, "videoUrls": { "title": "Video URLs", "type": "array", "description": "Deprecated: use the \"YouTube URLs\" field instead. Still accepted so existing runs keep working. YouTube video links or IDs. Leave empty to use the example videos.", "items": { "type": "string" } }, "channelUrls": { "title": "Channel URLs", "type": "array", "description": "Deprecated: use the \"YouTube URLs\" field instead. Still accepted so existing runs keep working. Channel links. Both forms work: https://www.youtube.com/@handle and https://www.youtube.com/channel/UC... The most recent videos are processed.", "default": [], "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in order of preference, for example en, de, tr. Falls back to the first available track.", "default": [ "en" ], "items": { "type": "string" } }, "translateTo": { "title": "Translate transcript to", "type": "string", "description": "Language code to translate the transcript into, for example es or de. Uses YouTube's own translation, so no extra cost. If a video does not offer that language, the original transcript is returned and a warning lists what it does offer." }, "preferManual": { "title": "Prefer human-written captions", "type": "boolean", "description": "Human-written captions are cleaner than auto-generated ones. Turn off to accept whichever comes first.", "default": true }, "includeTranscript": { "title": "Include transcript", "type": "boolean", "description": "Turn off to fetch only title, channel and thumbnail at the lower metadata price.", "default": true }, "chunkSeconds": { "title": "Paragraph length (seconds)", "minimum": 5, "maximum": 600, "type": "integer", "description": "Target length of each merged paragraph. Raw segments are always returned as well.", "default": 40 }, "maxVideosPerChannel": { "title": "Max videos per channel", "minimum": 1, "maximum": 200, "type": "integer", "description": "Deprecated: use the \"Max videos per source\" field instead. Still accepted so existing runs keep working. Upper limit of videos taken from each channel. Defaults to 30." }, "incremental": { "title": "Incremental mode", "type": "boolean", "description": "Skip videos already fetched with a transcript in a previous run. Keeps scheduled runs cheap. Metadata-only runs (Include transcript off) are not recorded this way and are charged again every time.", "default": true } } }, "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 } } } } } } } } } }