{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Captions & Subtitles for AI (Bulk)", "description": "Extract YouTube transcripts, captions and subtitles in bulk from video URLs or IDs. Manual or auto-generated tracks, any language, optional translation, plain text, timestamped segments, SRT or VTT. Ready for AI, RAG and LLM pipelines.", "version": "1.0", "x-build-id": "cygU7q1KYB0AXEtjk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/yasaslive~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-yasaslive-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/yasaslive~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-yasaslive-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/yasaslive~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-yasaslive-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "videoUrls" ], "properties": { "videoUrls": { "title": "YouTube videos", "minItems": 1, "type": "array", "description": "One video per line: watch URLs, youtu.be links, Shorts, embed and live URLs, or bare 11-character video IDs. Duplicates are fetched once.", "default": [ "https://www.youtube.com/watch?v=jNQXAC9IVRw" ], "items": { "type": "string" } }, "preferredLanguage": { "title": "Preferred language", "type": "string", "description": "Language code of the caption track to prefer, e.g. en, es, de, pt-BR. If the video has no track in this language, the best other track is used and its language is reported in the output.", "default": "en" }, "allowAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Use YouTube's automatic speech-recognition captions when no manually uploaded subtitles are available. Turn off to accept only human-made subtitles.", "default": true }, "translateTo": { "title": "Translate to (optional)", "type": "string", "description": "Language code to machine-translate the transcript into using YouTube's built-in caption translation, e.g. en, fr, ja. A native track in this language is used when one exists. Leave empty to keep the original language." }, "outputFormat": { "title": "Output formats", "type": "array", "description": "Plain text (transcriptText) is always included. Add timestamped segments, an SRT file body and/or a WebVTT file body.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments (JSON)", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments" ] }, "includeVideoDetails": { "title": "Include video details", "type": "boolean", "description": "Add channel name, channel ID, duration and view count to every item.", "default": true }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many videos to process in parallel.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "YouTube blocks datacenter IPs with a bot check, so Apify RESIDENTIAL proxy is the default and strongly recommended.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }