{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper", "description": "YouTube Transcript Scraper โ€” Extract YouTube video transcripts and subtitles, including spoken text, timestamps, language details, and video metadata. Useful for content repurposing, SEO research, video summarization, keyword analysis, and AI training workflows.", "version": "0.1", "x-build-id": "ZESBCOa2jFNdxpuDk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/socialdataapi~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-socialdataapi-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/socialdataapi~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-socialdataapi-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/socialdataapi~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-socialdataapi-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "urls" ], "properties": { "urls": { "title": "๐Ÿ”— YouTube video URLs", "type": "array", "description": "One or more YouTube video links: watch, youtu.be, shorts, embed or live links. An entry may also hold several links separated by commas. Each video is added to the dataset as soon as it is done; the same video listed twice is scraped once. On the free plan a run scrapes up to 20 videos.", "default": [], "items": { "type": "string" } }, "includeEnglishAG": { "title": "โœ… Include English auto-generated", "type": "boolean", "description": "Add YouTube's automatic English captions when the video has them.", "default": true }, "includeNonEnglish": { "title": "โœ… Include non-English transcripts", "type": "boolean", "description": "Add the transcripts in every other language the video offers.", "default": false }, "languageCode": { "title": "๐ŸŒ Language code (optional)", "type": "string", "description": "Leave empty to get the transcripts chosen by the two switches above. Enter a language code such as en, es, de or pt-BR to get exactly one transcript in that language instead: the video's own captions in that language, else the automatic ones, else YouTube's machine translation when available, else the original-language transcript (the row's message says which one you got).", "default": "" }, "outputFormat": { "title": "๐Ÿ“ฆ Output format", "enum": [ "timestamp", "text" ], "type": "string", "description": "How each transcript's content is written: Plain text gives one clean string; Timestamped cues gives a list of lines with start and end times. The transcript field always holds timed lines.", "default": "text" }, "fetchVideoMetadata": { "title": "โœ… Fetch video details", "type": "boolean", "description": "Adds description, publish date, category, tags, thumbnails, duration, view and like counts, live status and channel name, ID, link and verified badge.", "default": false }, "includeEngagementMetrics": { "title": "โœ… Compute engagement analytics", "type": "boolean", "description": "Adds engagementRate (likes รท views), estimatedSpeakingRateWpm (words per minute of video) and transcriptCoveragePercent (how much of the video the captions cover), calculated from the video details and the first transcript. Switches on video details automatically.", "default": false }, "includeChannelInfo": { "title": "โœ… Include channel subscriber count", "type": "boolean", "description": "Adds the channel's subscriber count from its About page. Switches on video details automatically. Some channels don't show it; then the count stays empty and channelInfoCoverage says why - never a guessed number.", "default": false }, "proxyConfiguration": { "title": "๐ŸŒ Proxy configuration", "type": "object", "description": "Leave it off for the usual run: the first try goes direct and retries go through Apify's residential proxy. A proxy you choose here is used for every request.", "default": {} } } }, "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 } } } } } } } } } }