{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper: Captions in Any Language", "description": "Get YouTube transcripts in the language you asked for, with one row per video and a clear status for every failure. Matches regional tracks (pt to pt-BR), flags machine translation, and outputs JSON, text, SRT, VTT or LLM-ready text. You pay only for transcripts retrieved.", "version": "1.0", "x-build-id": "2pTgHfXFGFdWkyKtC" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/subrosa~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-subrosa-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/subrosa~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-subrosa-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/subrosa~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-subrosa-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "videoUrls": { "title": "YouTube videos", "type": "array", "description": "YouTube URLs or bare 11-character video ids. Accepts watch, youtu.be, shorts, embed, live and youtube-nocookie links. You get exactly one dataset row per item, whether it succeeds or fails.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs (alternative input)", "type": "array", "description": "Same thing as the field above, in Apify's request-list format. Useful when this Actor is called from another Actor or from a webhook.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "language": { "title": "Language", "type": "string", "description": "BCP-47 language code, e.g. \"en\", \"pt\", \"pt-BR\", \"es-419\". Asking for \"pt\" correctly matches YouTube's \"pt-BR\" track. Leave empty to take the video's default track. The output always tells you which language you actually got and how." }, "preferManual": { "title": "Prefer human-written captions", "type": "boolean", "description": "When a video has both human-written and auto-generated captions in the same language, take the human ones. Auto-generated captions are noticeably noisier.", "default": true }, "allowTranslation": { "title": "Allow machine translation", "type": "boolean", "description": "If the requested language has no caption track, fall back to YouTube's machine translation. The output marks these rows with translated: true so you never mistake them for native captions. Turn this off to get a clean language_unavailable status instead.", "default": true }, "format": { "title": "Output format", "enum": [ "json", "text", "srt", "vtt", "llm" ], "type": "string", "description": "json keeps the timestamped cue array. text is one clean paragraph. srt and vtt are subtitle files. llm is paragraph-chunked text with time anchors, sized for feeding into a language model.", "default": "json" }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Add title, channel, duration, view count and live status to each row.", "default": true }, "maxConcurrency": { "title": "Concurrent requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to fetch at once. Raise it for speed, lower it if you are running without a proxy and hitting rate limits.", "default": 5 }, "requestTimeoutSecs": { "title": "Request timeout (seconds)", "minimum": 5, "maximum": 120, "type": "integer", "description": "Per-request timeout before the Actor gives up and retries.", "default": 20 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Leave this on residential. YouTube answers datacenter IP addresses with a sign-in wall, so a datacenter proxy returns login_required for most videos even though nothing is wrong with the request. Residential addresses behave normally. Without any proxy at all, YouTube starts returning empty caption bodies partway through a large run.", "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 } } } } } } } } } }