{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Subtitles, Captions & Channels", "description": "Extract YouTube transcripts, subtitles & captions in bulk — from video URLs, entire channels, playlists, or search. Timestamped segments, SRT/VTT, auto + manual captions, translation to 100+ languages, rich video metadata, and monitoring for new uploads. No login, no API key, no browser.", "version": "0.1", "x-build-id": "UMS0wJEiSTLM3ph9j" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/scrapesage~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-scrapesage-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/scrapesage~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-scrapesage-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/scrapesage~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-scrapesage-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Video URLs or IDs", "type": "array", "description": "YouTube video URLs or 11-character video IDs. All formats work: watch URLs, youtu.be, Shorts, embeds, live URLs.", "items": { "type": "string" } }, "channelUrls": { "title": "Channel URLs or @handles", "type": "array", "description": "Channels to expand into their latest videos — @handle, full URL, or UC… channel ID. Combine with Monitor mode to transcribe only newly uploaded videos on a schedule.", "items": { "type": "string" } }, "playlistUrls": { "title": "Playlist URLs or IDs", "type": "array", "description": "Playlists to expand into videos (playlist URL or PL…/UU… ID).", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "YouTube search keywords — each query is expanded into its top result videos.", "items": { "type": "string" } }, "startUrls": { "title": "Start URLs (auto-detected)", "type": "array", "description": "Paste any YouTube URLs — video, Shorts, playlist, channel, or search-results pages are detected automatically.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "searchSort": { "title": "Search sort order", "enum": [ "relevance", "date", "views", "rating" ], "type": "string", "description": "How search-query results are ordered before taking the top videos.", "default": "relevance" }, "language": { "title": "Preferred transcript language", "type": "string", "description": "ISO language code (en, es, de, fr, pt, hi, ja, ko, zh…). The scraper picks a human-written track in this language first, then auto-generated captions (see fallbacks below).", "default": "en" }, "fallbackToAutoCaptions": { "title": "Fall back to auto-generated captions", "type": "boolean", "description": "When no human-written track exists in the preferred language, use YouTube's auto-generated (ASR) captions.", "default": true }, "fallbackToAnyLanguage": { "title": "Fall back to any available language", "type": "boolean", "description": "When nothing exists in the preferred language at all, take the video's default/original caption track instead of skipping the video.", "default": true }, "translateTo": { "title": "Translate transcripts to", "type": "string", "description": "Optional ISO language code — uses YouTube's own caption translation (100+ languages, e.g. en, es, fr, de, pt, ar, hi, ja). Leave empty for the original language." }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Include the segments array ({ start, dur, end, text } in seconds) alongside the plain-text transcript.", "default": true }, "includeSrt": { "title": "Include SRT subtitle file content", "type": "boolean", "description": "Add an srt field with ready-to-save SubRip subtitles.", "default": false }, "includeVtt": { "title": "Include WebVTT subtitle file content", "type": "boolean", "description": "Add a vtt field with ready-to-save WebVTT subtitles.", "default": false }, "includeVideoMetadata": { "title": "Include rich video metadata", "type": "boolean", "description": "Title, channel, views, likes, publish date, duration, category, keywords and chapters on every record (no extra requests — it comes from the same page).", "default": true }, "monitorMode": { "title": "Monitor mode (only new videos)", "type": "boolean", "description": "Remember every video already delivered and emit only videos not seen in previous runs. Combine with an Apify Schedule on channel/playlist/search inputs to get transcripts of new uploads only — the schedule triggers the runs, monitor mode deduplicates across them.", "default": false }, "maxResults": { "title": "Max results (total)", "minimum": 0, "type": "integer", "description": "Stop after this many records in total. 0 = no limit (opt-in; mind the run timeout on huge sweeps).", "default": 25 }, "maxVideosPerSource": { "title": "Max videos per channel/playlist/search", "minimum": 0, "type": "integer", "description": "Per-source expansion cap so one huge channel can't crowd out the others. 0 = use the global limit.", "default": 25 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Residential proxies strongly recommended — YouTube limits caption downloads from datacenter IPs.", "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 } } }, "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 } } } } } } } } } }