{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper", "description": "Collect public YouTube captions with real timestamps, language selection and optional text exports. Also validate and search supplied transcript records. No paid transcript API or Google API key required.", "version": "1.4", "x-build-id": "VPqcQ6KcCzh8Q7plF" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/thescrapelab~Apify-YouTube-Transcript-Scraper-2-0/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-thescrapelab-Apify-YouTube-Transcript-Scraper-2-0", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/thescrapelab~Apify-YouTube-Transcript-Scraper-2-0/runs": { "post": { "operationId": "runs-sync-thescrapelab-Apify-YouTube-Transcript-Scraper-2-0", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/thescrapelab~Apify-YouTube-Transcript-Scraper-2-0/run-sync": { "post": { "operationId": "run-sync-thescrapelab-Apify-YouTube-Transcript-Scraper-2-0", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "videoUrls": { "title": "Video URLs", "type": "array", "description": "Public YouTube video URLs, Shorts, live video URLs or 11-character IDs. Used when no supplied records or dataset are selected.", "default": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ], "items": { "type": "string" } }, "maxResults": { "title": "Maximum caption rows", "minimum": 1, "maximum": 100000, "type": "integer", "description": "Maximum delivered caption segments across all videos. The Console preview uses 10. Omit in API input to preserve the existing unlimited-row behavior; maxChars still caps each video." }, "preferredLanguages": { "title": "Preferred languages", "type": "array", "description": "Preferred caption language codes, in order. An available language is used when none of these exists.", "default": [ "en", "en-us" ], "items": { "type": "string" } }, "providedRecords": { "title": "Your records (JSON)", "type": "array", "description": "Optional transcript records to validate and analyze instead of fetching videos. Leave empty for live YouTube collection. Use this or an accessible Apify dataset, not both.", "items": { "type": "object" } }, "providedDatasetId": { "title": "Your Apify dataset ID", "type": "string", "description": "Optional 17-character ID of a dataset you can access. Clear the JSON records to [] when using a dataset. Only a bounded number of records is read." }, "providedRecordLimit": { "title": "Maximum evidence records", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Maximum supplied records scanned across this run, including duplicates and rejected records. Use at least two relevant records for comparisons.", "default": 1 }, "maxChars": { "title": "Max transcript chars", "minimum": 1000, "type": "integer", "description": "Maximum combined transcript characters per video. Timestamps come from actual caption cues; truncated coverage is reported.", "default": 1000 }, "fetchVideoMeta": { "title": "Fetch video metadata", "type": "boolean", "description": "Fetch the video title and channel from its public YouTube watch page.", "default": false }, "maxVideoRuntimeSecs": { "title": "Per-video runtime limit (seconds)", "minimum": 30, "maximum": 240, "type": "integer", "description": "Maximum collection time per video, bounded by the run timeout.", "default": 60 }, "useResidentialProxy": { "title": "Use residential proxy (advanced)", "type": "boolean", "description": "The preview enables Apify residential routing because YouTube blocks datacenter IPs. Disable it for cheaper automatic routing where that works. Proxy traffic is a platform cost, not a paid data API. API clients omitting this field retain the false default.", "default": false }, "youtubeCookies": { "title": "YouTube cookies (optional)", "type": "string", "description": "Optional YouTube session cookies retained for compatibility. Captions do not require a Google API key or a paid provider." }, "exportVideoText": { "title": "Export one text document per video", "type": "boolean", "description": "Also save one combined text document per successfully delivered video in the run key-value store. No additional transcript event.", "default": false }, "analysisQuery": { "title": "Find a phrase in your evidence", "type": "string", "description": "Optional literal phrase. EVIDENCE_ANALYSIS links matching delivered records; no inferred sentiment or model response." } } }, "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 } } } } } } } } } }