{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript & Subtitles Scraper", "description": "Paste YouTube video URLs or IDs, channels, playlists or searches, in bulk. Get each transcript as plain text with timestamps, title, channel and date. At no extra cost: views, likes, tags, chapters, SRT and VTT subtitles, LLM text, RAG chunks by chapter. $3 per 1,000, videos without captions free.", "version": "1.0", "x-build-id": "24SQ9Y6udmVnZhnT2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/heyitsgautham~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-heyitsgautham-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/heyitsgautham~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-heyitsgautham-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/heyitsgautham~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-heyitsgautham-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": { "videos": { "title": "YouTube videos", "type": "array", "description": "Video URLs or 11-character video IDs. Accepts watch, youtu.be, Shorts, embed and live links. For whole channels, playlists or searches use the next two fields.", "items": { "type": "string" } }, "channelsAndPlaylists": { "title": "Channels and playlists", "type": "array", "description": "Optional. YouTube channel or playlist URLs, expanded into their videos. Accepts @handle, /channel/UC..., /c/... and /user/... links, playlist links with list=..., and bare @handles, UC channel IDs or PL playlist IDs. Channels go newest first. Each video is charged like any other transcript.", "items": { "type": "string" } }, "searchQueries": { "title": "Search queries", "type": "array", "description": "Optional. YouTube searches, each expanded into its top videos in YouTube's order. Each video is charged like any other transcript, and the search itself is free.", "items": { "type": "string" } }, "maxVideosPerSource": { "title": "Max videos per channel, playlist or search", "minimum": 0, "maximum": 20000, "type": "integer", "description": "How many videos to take from each channel, playlist or search. 0 means all videos, up to 20,000. Does not limit the videos field.", "default": 100 }, "includeShorts": { "title": "Include Shorts", "type": "boolean", "description": "Channels only. Off: regular videos and past live streams. On: every upload, Shorts included.", "default": false }, "language": { "title": "Transcript language", "type": "string", "description": "ISO 639-1 code such as en, es, hi or de. Uses captions in this language when the video has them. Otherwise returns the video's original captions and sets requestedLanguageFound to false.", "default": "en" }, "includeTimestamps": { "title": "Include timestamped segments", "type": "boolean", "description": "Adds a segments array with start time, duration and text for each caption line. The plain transcript is always included.", "default": true }, "includeVideoDetails": { "title": "Include video details", "type": "boolean", "description": "Adds viewCount, likeCount, commentCount, category, description, tags, thumbnailUrl and chapters (from the description's timestamps, each with a url that opens the video there) to each transcript row, at no extra cost. Emails and phone numbers in descriptions are replaced with [email removed] and [phone removed].", "default": false }, "outputFormats": { "title": "Output formats", "uniqueItems": true, "type": "array", "description": "Extra fields on each transcript row, at no extra cost. text: plainText, the captions as paragraphs, one per line. llm: llmText, Markdown with the title, channel, date and URL on top, chapter headings, a [m:ss] stamp per paragraph and sound cues such as [Music] removed. srt and vtt: the subtitle file as text. chunks: a chunks array for RAG, one chunk per YouTube chapter, long chapters split evenly, or even pieces when the video has no chapters, each with start, end, text, wordCount and a url that opens the video at that second.", "items": { "type": "string", "enum": [ "text", "llm", "srt", "vtt", "chunks" ], "enumTitles": [ "Plain text in paragraphs", "LLM-ready Markdown", "SRT subtitles", "VTT subtitles", "RAG chunks by chapter" ] }, "default": [] }, "chunkSizeWords": { "title": "Chunk size (words)", "minimum": 50, "maximum": 5000, "type": "integer", "description": "Used by the chunks format. A chunk holds at most about this many words, cut between caption lines. Chapters shorter than this stay one chunk.", "default": 300 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 50, "type": "integer", "description": "How many videos to fetch in parallel.", "default": 10 }, "useProxy": { "title": "Use residential proxy", "type": "boolean", "description": "Leave on. YouTube blocks cloud IPs.", "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 } } } } } } } } } }