{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Extractor", "description": "YouTube transcripts from videos, playlists, channels or a search, in any language: text, SRT, VTT, JSON, RAG-ready chunks and chapters. Auto-translation, free language check, failed videos are free.", "version": "0.0", "x-build-id": "3k42AKIAhbutUKT4o" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lsso~youtube-transcript-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lsso-youtube-transcript-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lsso~youtube-transcript-extractor/runs": { "post": { "operationId": "runs-sync-lsso-youtube-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lsso~youtube-transcript-extractor/run-sync": { "post": { "operationId": "run-sync-lsso-youtube-transcript-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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, playlists or channels", "type": "array", "description": "Video URLs (watch, youtu.be, shorts, live), video IDs, playlist URLs, or channel URLs / @handles. Playlists and channels are expanded automatically (newest first for channels). Optional if you use *Search YouTube*.", "items": { "type": "string" } }, "searchQueries": { "title": "Search YouTube (optional)", "type": "array", "description": "Search terms, e.g. `andrej karpathy llm`. The top videos for each search are added to the run (relevance order), so you don't need to collect URLs first.", "default": [], "items": { "type": "string" } }, "maxResultsPerSearch": { "title": "Videos per search", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many videos to take from each search.", "default": 20 }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in order of preference, e.g. `en`, `es`, `ko`, `ja`, `zh-Hans` (Simplified Chinese), `zh-Hant` (Traditional), `pt-BR`. If the video has no captions in these languages and *Translate* is on, the transcript is translated into the first one. Leave empty to get the video's original language.", "default": [], "items": { "type": "string" } }, "translate": { "title": "Translate when the language is missing", "type": "boolean", "description": "When none of the preferred languages exists for a video, translate the captions into the first preferred language (~100 languages). YouTube's own translation is tried first; when YouTube rate-limits it (common), the original captions are translated with Google Translate, keeping every timestamp. The output field `translationEngine` says which one was used.", "default": true }, "outputFormats": { "title": "Output formats", "uniqueItems": true, "type": "array", "description": "Which fields to include per video: `text` (plain transcript), `segments` (timed cues as JSON), `timestamped` (`[mm:ss] text` lines), `paragraphs` (readable ~1-minute paragraphs), `srt`, `vtt`, `chunks` (RAG-ready ~300-word pieces with start/end time and a deep link), `chapters` (transcript split by the video's chapters, when the description has them).", "items": { "type": "string", "enum": [ "text", "segments", "timestamped", "paragraphs", "srt", "vtt", "chunks", "chapters" ], "enumTitles": [ "Plain text", "Timed segments (JSON)", "Timestamped text", "Paragraphs", "SRT subtitles", "WebVTT subtitles", "RAG chunks (for AI / vector DBs)", "Text per chapter" ] }, "default": [ "text", "segments" ] }, "chunkWords": { "title": "Words per chunk", "minimum": 50, "maximum": 5000, "type": "integer", "description": "Target size of each item in `chunks` (CJK characters count as words). Chunks end at caption boundaries.", "default": 300 }, "listLanguagesOnly": { "title": "Only list available caption languages (free)", "type": "boolean", "description": "Don't download transcripts; just return each video's caption tracks (language, human/auto, translatable) and metadata. Not charged — use it to check what exists before a big run.", "default": false }, "preferManual": { "title": "Prefer human-made captions", "type": "boolean", "description": "When both human-uploaded and auto-generated captions exist, pick the human-made ones.", "default": true }, "includeAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Turn off to return only human-made captions (videos with auto-captions only will be reported as having no transcript).", "default": true }, "maxVideos": { "title": "Max videos", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Upper limit of videos processed in this run (applies after expanding playlists and channels).", "default": 50 }, "concurrency": { "title": "Concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to process in parallel.", "default": 5 }, "maxRetries": { "title": "Retries per video", "minimum": 0, "maximum": 10, "type": "integer", "description": "Each retry uses a fresh proxy session and a different YouTube client.", "default": 4 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "YouTube blocks datacenter IPs, so Apify residential proxies are used by default. Proxy traffic is tiny (about 0.3 MB per video).", "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 } } } } } } } } } }