{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper Pro (Captions + AI Fallback)", "description": "Extract YouTube transcripts at scale without burning through your budget. It starts with free captions whenever they're available, then switches to AI only for videos that don't have them. You stay in control of costs, and the output — JSON, SRT, VTT, plain text, or LLM-ready format", "version": "1.0", "x-build-id": "kTKb9L7WT77UeaUao" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/codepoetry~youtube-transcript-ai-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-codepoetry-youtube-transcript-ai-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/codepoetry~youtube-transcript-ai-scraper/runs": { "post": { "operationId": "runs-sync-codepoetry-youtube-transcript-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/codepoetry~youtube-transcript-ai-scraper/run-sync": { "post": { "operationId": "run-sync-codepoetry-youtube-transcript-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "startUrls" ], "properties": { "startUrls": { "title": "YouTube URLs", "type": "array", "description": "Paste one or more YouTube URLs — single videos, playlists, or channels. Supports watch URLs, short youtu.be links, and channel URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxResults": { "title": "Max videos per playlist/channel", "minimum": 1, "type": "integer", "description": "Maximum number of videos to fetch from a playlist or channel. Single video URLs ignore this. Channels return newest videos first.", "default": 10 }, "languages": { "title": "Caption languages", "type": "array", "description": "Languages to try, in order of preference. The first match on each video is used. Note: setting Caption source to Manual Only means auto-generated captions are ignored even if they exist in your requested language.", "items": { "type": "string", "enum": [ "af", "ak", "sq", "am", "ar", "hy", "as", "ay", "az", "bn", "eu", "be", "bho", "bs", "bg", "my", "ca", "ceb", "zh", "zh-CN", "zh-HK", "zh-SG", "zh-TW", "zh-Hans", "zh-Hant", "co", "hr", "cs", "da", "dv", "nl", "en", "en-US", "eo", "et", "ee", "fil", "fi", "fr", "gl", "lg", "ka", "de", "el", "gn", "gu", "ht", "ha", "haw", "he", "hi", "hmn", "hu", "is", "ig", "id", "ga", "it", "ja", "jv", "kn", "kk", "km", "rw", "ko", "kri", "ku", "ky", "lo", "la", "lv", "ln", "lt", "lb", "mk", "mg", "ms", "ml", "mt", "mi", "mr", "mn", "ne", "nso", "no", "ny", "or", "om", "ps", "fa", "pl", "pt", "pa", "qu", "ro", "ru", "sm", "sa", "gd", "sr", "sn", "sd", "si", "sk", "sl", "so", "st", "es", "su", "sw", "sv", "tg", "ta", "tt", "te", "th", "ti", "ts", "tr", "tk", "uk", "ur", "ug", "uz", "vi", "cy", "fy", "xh", "yi", "yo", "zu" ], "enumTitles": [ "af — Afrikaans", "ak — Akan", "sq — Albanian", "am — Amharic", "ar — Arabic", "hy — Armenian", "as — Assamese", "ay — Aymara", "az — Azerbaijani", "bn — Bangla", "eu — Basque", "be — Belarusian", "bho — Bhojpuri", "bs — Bosnian", "bg — Bulgarian", "my — Burmese", "ca — Catalan", "ceb — Cebuano", "zh — Chinese", "zh-CN — Chinese (China)", "zh-HK — Chinese (Hong Kong)", "zh-SG — Chinese (Singapore)", "zh-TW — Chinese (Taiwan)", "zh-Hans — Chinese (Simplified)", "zh-Hant — Chinese (Traditional)", "co — Corsican", "hr — Croatian", "cs — Czech", "da — Danish", "dv — Divehi", "nl — Dutch", "en — English", "en-US — English (United States)", "eo — Esperanto", "et — Estonian", "ee — Ewe", "fil — Filipino", "fi — Finnish", "fr — French", "gl — Galician", "lg — Ganda", "ka — Georgian", "de — German", "el — Greek", "gn — Guarani", "gu — Gujarati", "ht — Haitian Creole", "ha — Hausa", "haw — Hawaiian", "he — Hebrew", "hi — Hindi", "hmn — Hmong", "hu — Hungarian", "is — Icelandic", "ig — Igbo", "id — Indonesian", "ga — Irish", "it — Italian", "ja — Japanese", "jv — Javanese", "kn — Kannada", "kk — Kazakh", "km — Khmer", "rw — Kinyarwanda", "ko — Korean", "kri — Krio", "ku — Kurdish", "ky — Kyrgyz", "lo — Lao", "la — Latin", "lv — Latvian", "ln — Lingala", "lt — Lithuanian", "lb — Luxembourgish", "mk — Macedonian", "mg — Malagasy", "ms — Malay", "ml — Malayalam", "mt — Maltese", "mi — Māori", "mr — Marathi", "mn — Mongolian", "ne — Nepali", "nso — Northern Sotho", "no — Norwegian", "ny — Nyanja", "or — Odia", "om — Oromo", "ps — Pashto", "fa — Persian", "pl — Polish", "pt — Portuguese", "pa — Punjabi", "qu — Quechua", "ro — Romanian", "ru — Russian", "sm — Samoan", "sa — Sanskrit", "gd — Scottish Gaelic", "sr — Serbian", "sn — Shona", "sd — Sindhi", "si — Sinhala", "sk — Slovak", "sl — Slovenian", "so — Somali", "st — Southern Sotho", "es — Spanish", "su — Sundanese", "sw — Swahili", "sv — Swedish", "tg — Tajik", "ta — Tamil", "tt — Tatar", "te — Telugu", "th — Thai", "ti — Tigrinya", "ts — Tsonga", "tr — Turkish", "tk — Turkmen", "uk — Ukrainian", "ur — Urdu", "ug — Uyghur", "uz — Uzbek", "vi — Vietnamese", "cy — Welsh", "fy — Western Frisian", "xh — Xhosa", "yi — Yiddish", "yo — Yoruba", "zu — Zulu" ] }, "default": [ "en" ] }, "subType": { "title": "Caption source", "enum": [ "manual", "auto", "both" ], "type": "string", "description": "Manual = human-written captions only. Auto = YouTube's machine-generated captions only. Both = tries manual first, falls back to auto. Most videos only have auto-generated captions.", "default": "both" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Plain Text is the simplest — one block of words. JSON adds timestamps. LLM-Ready strips [Music] and filler tokens for AI pipelines. SRT and VTT are subtitle formats for video editors.", "items": { "type": "string", "enum": [ "json", "text", "llm", "srt", "vtt" ], "enumTitles": [ "JSON (timestamped segments)", "Plain Text", "LLM-Ready (filler stripped)", "SRT (subtitle file)", "VTT (WebVTT)" ] }, "default": [ "json", "text", "llm" ] }, "wordLevel": { "title": "Word-level timestamps", "type": "boolean", "description": "Add per-word start and end times inside each JSON segment.", "default": false }, "enableAiFallback": { "title": "Enable AI transcription", "type": "boolean", "description": "Off by default. Turn on to transcribe videos that have no native YouTube captions. Memory increases to 4 GB automatically and per-minute AI charges apply.", "default": false }, "forceWhisperLanguage": { "title": "AI transcription language", "enum": [ "", "af", "am", "ar", "as", "az", "ba", "be", "bg", "bn", "bo", "br", "bs", "ca", "cs", "cy", "da", "de", "el", "en", "es", "et", "eu", "fa", "fi", "fo", "fr", "gl", "gu", "ha", "haw", "he", "hi", "hr", "ht", "hu", "hy", "id", "is", "it", "ja", "jw", "ka", "kk", "km", "kn", "ko", "la", "lb", "ln", "lo", "lt", "lv", "mg", "mi", "mk", "ml", "mn", "mr", "ms", "mt", "my", "ne", "nl", "nn", "no", "oc", "pa", "pl", "ps", "pt", "ro", "ru", "sa", "sd", "si", "sk", "sl", "sn", "so", "sq", "sr", "su", "sv", "sw", "ta", "te", "tg", "th", "tl", "tr", "tt", "uk", "ur", "uz", "vi", "yi", "yo", "yue", "zh" ], "type": "string", "description": "Force the AI model to a specific language and skip the 30-second detection window at the start of each video. Saves roughly 20% of AI transcription time per video. Leave empty to auto-detect." }, "maxAiMinutes": { "title": "Max AI minutes per run", "minimum": 0, "type": "integer", "description": "Hard cap on total AI transcription minutes for this run. When reached, remaining caption-free videos are skipped and the run continues. Set to 0 for unlimited.", "default": 30 }, "skipAiFallbackIfLongerThan": { "title": "Skip AI for long videos (minutes)", "minimum": 0, "type": "integer", "description": "Skip AI transcription for any video longer than this many minutes. Useful when a channel mixes short clips with long recordings. Set to 0 to disable.", "default": 0 } } }, "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 } } } } } } } } } }