{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Captions, SRT, VTT & RAG", "description": "Unofficial and not affiliated with YouTube or Google. Extract clean, timestamped transcripts from public videos and Shorts with language selection, translation, subtitles, Markdown, and RAG-ready chunks.", "version": "1.0", "x-build-id": "WbaQttJNwEDJ8qTCv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sebastian-actors~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sebastian-actors-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sebastian-actors~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-sebastian-actors-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sebastian-actors~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-sebastian-actors-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "videoUrls" ], "properties": { "videoUrls": { "title": "YouTube video URLs or IDs", "minItems": 1, "maxItems": 1000, "type": "array", "description": "Individual YouTube video URLs or raw 11-character video IDs. Channels, playlists, profiles, and search pages are returned as per-item errors.", "items": { "type": "string", "minLength": 1, "maxLength": 2048 } }, "preferredLanguages": { "title": "Preferred languages", "maxItems": 20, "uniqueItems": true, "type": "array", "description": "Ordered BCP 47 language preferences. Exact regional matches beat base-language matches.", "items": { "type": "string", "enumSuggestedValues": [ "en", "en-US", "es", "es-419", "fr", "de", "pt", "pt-BR", "it", "ja", "ko", "zh-Hans", "zh-Hant", "ar", "hi" ], "enumTitles": [ "English", "English (United States)", "Spanish", "Spanish (Latin America)", "French", "German", "Portuguese", "Portuguese (Brazil)", "Italian", "Japanese", "Korean", "Chinese (Simplified)", "Chinese (Traditional)", "Arabic", "Hindi" ] }, "default": [ "en" ] }, "captionPreference": { "title": "Caption preference", "enum": [ "manual-first", "auto-first", "manual-only", "auto-only" ], "type": "string", "description": "Choose whether human-created or automatically generated captions are preferred or required.", "default": "manual-first" }, "fallbackToAnyLanguage": { "title": "Fallback to any language", "type": "boolean", "description": "Select another available language when no preferred language matches.", "default": true }, "translateTo": { "title": "Translate to", "minLength": 2, "maxLength": 35, "type": "string", "description": "Optional YouTube-supported target language code. Existing native target-language captions are preferred." }, "outputFormats": { "title": "Output formats", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Transcript artifacts to include in each successful result.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt", "markdown", "chunks" ], "enumTitles": [ "Plain text", "Timestamped segments", "SRT subtitles", "WebVTT subtitles", "Markdown", "RAG chunks" ] }, "default": [ "text", "segments" ] }, "cleaning": { "title": "Transcript cleaning", "type": "object", "description": "Configure deterministic text normalization. No punctuation is invented.", "properties": { "decodeHtmlEntities": { "title": "Decode HTML entities", "description": "Decode entities such as &.", "type": "boolean", "editor": "checkbox", "default": true }, "normalizeWhitespace": { "title": "Normalize whitespace", "description": "Collapse internal whitespace and trim segment text.", "type": "boolean", "editor": "checkbox", "default": true }, "normalizeUnicode": { "title": "Normalize Unicode", "description": "Normalize text to Unicode NFC.", "type": "boolean", "editor": "checkbox", "default": true }, "deduplicateAdjacentSegments": { "title": "Deduplicate adjacent segments", "description": "Remove only exact adjacent text with substantially overlapping timestamps.", "type": "boolean", "editor": "checkbox", "default": true }, "removeNonSpeechCues": { "title": "Remove non-speech cues", "description": "Remove standalone cues such as [Music] and [Applause].", "type": "boolean", "editor": "checkbox", "default": false }, "paragraphGapSeconds": { "title": "Paragraph gap", "description": "Start a new paragraph after a gap of this many seconds.", "type": "number", "editor": "number", "minimum": 0, "maximum": 60, "default": 2.5, "unit": "seconds" } }, "default": { "decodeHtmlEntities": true, "normalizeWhitespace": true, "normalizeUnicode": true, "deduplicateAdjacentSegments": true, "removeNonSpeechCues": false, "paragraphGapSeconds": 2.5 }, "additionalProperties": false }, "chunking": { "title": "RAG chunking", "type": "object", "description": "Configure segment-aware chunks generated when the chunks format is selected.", "properties": { "maxCharacters": { "title": "Maximum characters", "description": "Maximum Unicode code points per chunk.", "type": "integer", "editor": "number", "minimum": 250, "maximum": 20000, "default": 2000 }, "overlapCharacters": { "title": "Overlap characters", "description": "Approximate overlap retained as whole segments.", "type": "integer", "editor": "number", "minimum": 0, "maximum": 19999, "default": 200 }, "includeTimestamps": { "title": "Include timestamps", "description": "Prefix chunk segments with their start timestamps.", "type": "boolean", "editor": "checkbox", "default": true } }, "default": { "maxCharacters": 2000, "overlapCharacters": 200, "includeTimestamps": true }, "additionalProperties": false }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Include available title, channel, duration, publication, thumbnail, Shorts, and live metadata.", "default": true }, "maxConcurrency": { "title": "Maximum concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Number of videos processed concurrently.", "default": 5 }, "maxRetriesPerVideo": { "title": "Retries per video", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of complete session retries after the first attempt.", "default": 3 }, "requestTimeoutSecs": { "title": "Request timeout", "minimum": 10, "maximum": 120, "type": "integer", "description": "Timeout applied to each upstream HTTP request.", "default": 30 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Use Apify Proxy or your own proxy URLs for YouTube requests.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "debug": { "title": "Debug logging", "type": "boolean", "description": "Log sanitized phase diagnostics without transcripts, cookies, tokens, response bodies, or proxy URLs.", "default": false } } }, "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 } } } } } } } } } }