{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Bulk Captions & Subtitles", "description": "Get YouTube transcripts in bulk: clean text, timestamped lines and SRT/VTT subtitles for any list of videos, Shorts and live replays, with title, channel and views. Original language or any caption language. Ready for AI, RAG and automation.", "version": "1.0", "x-build-id": "HdQgsIzpteX6YPw0r" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vero-api~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vero-api-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vero-api~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-vero-api-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vero-api~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-vero-api-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Paste one or many YouTube video links or 11-character video IDs. Watch links, youtu.be links, Shorts and live replays all work, and you get one transcript per video. Use links to individual videos, not playlist or channel pages.", "items": { "type": "string" } }, "transcriptLanguage": { "title": "Transcript language", "type": "string", "description": "Pick a language or type any YouTube caption code, such as en, pt-BR, zh-Hant or iw. Leave it on Auto-detect to get the language spoken in each video. A base code like en also matches regional captions such as en-US, and human-made captions come first. A video without captions in this language gets a free row listing the languages it does offer.", "default": "auto" }, "fallbackLanguages": { "title": "Fallback languages", "type": "array", "description": "Language codes to try, in order, when a video has no captions in the transcript language, for example es and then en. Add auto at the end to fall back to the language spoken in the video.", "default": [], "items": { "type": "string" } }, "captionType": { "title": "Caption type", "enum": [ "any", "manual", "generated" ], "type": "string", "description": "Which captions to accept. Any takes human-made captions first and auto-generated ones when that is all a video has.", "default": "any" }, "additionalFormats": { "title": "Additional subtitle formats", "type": "array", "description": "Also include the transcript as ready-to-use subtitle files in the chosen formats.", "items": { "type": "string", "enum": [ "srt", "vtt" ], "enumTitles": [ "SubRip (.srt)", "WebVTT (.vtt)" ] }, "default": [] }, "includeTimestamps": { "title": "Include timestamped segments", "type": "boolean", "description": "Include the segments list: every caption line with its start time and duration in seconds. Turn it off for plain text only.", "default": true }, "includeVideoDetails": { "title": "Include video details", "type": "boolean", "description": "Add the video's title, channel name, channel URL, thumbnail, view count, description, tags and live-stream status. Included at no extra cost.", "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 }, "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 } } } } } } } } } }