{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Captions & Subtitles", "description": "YouTube transcript API and YouTube to text: videos, channels and playlists as timestamped caption lines, the full transcript, and SRT or WebVTT subtitles to download at no extra charge. 220 languages by name, or all a video has. Title, channel, views and length included. No captions, no charge.", "version": "0.1", "x-build-id": "pDoOTrLycCGXNbrWn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kaleidoscopelabs~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kaleidoscopelabs-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kaleidoscopelabs~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-kaleidoscopelabs-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kaleidoscopelabs~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-kaleidoscopelabs-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Videos, channels or playlists", "minItems": 1, "type": "array", "description": "What to read, one per line: a video's link (watch, youtu.be, Shorts, embed, live) or its 11-character ID; a channel's link (https://www.youtube.com/@NASA, /channel/…, /c/…, /user/…), for its uploaded videos, newest first; or a playlist's link (with list=). A watch link inside a playlist reads that video. A line that is none of these is skipped and said in the log.", "default": [ "https://www.youtube.com/watch?v=Zezt6EsG9WE", "https://www.youtube.com/@NASA" ], "items": { "type": "string" } }, "languages": { "title": "Languages", "type": "array", "description": "The transcript's languages, a record per video and language: uploaded captions first, then automatic ones; English takes any English track. Leave it empty for each video's own language (the one spoken in it). Each language returned is one transcript.", "items": { "type": "string", "enum": [ "af", "agq", "ak", "sq", "am", "ar", "hy", "as", "ast", "asa", "az", "ksf", "bm", "bn", "bas", "eu", "be", "bem", "bez", "brx", "bs", "br", "bg", "my", "yue", "ca", "ceb", "tzm", "ckb", "ccp", "ce", "chr", "cgg", "zh", "zh-Hans", "zh-Hant", "ksh", "kw", "co", "hr", "cs", "da", "dua", "nl", "dz", "ebu", "en", "en-US", "en-GB", "eo", "et", "ee", "ewo", "fo", "fil", "fi", "fr", "fr-CA", "fur", "ff", "gl", "lg", "ka", "de", "el", "gu", "guz", "ht", "ha", "haw", "he", "hi", "hmn", "hu", "is", "ig", "smn", "id", "ga", "it", "ja", "jv", "dyo", "kea", "kab", "kkj", "kl", "kln", "kam", "kn", "ks", "kk", "km", "ki", "rw", "kok", "ko", "khq", "ses", "ku", "nmg", "ky", "lkt", "lag", "lo", "la", "lv", "ln", "lt", "dsb", "lu", "luo", "lb", "luy", "mk", "jmc", "mgh", "kde", "mg", "ms", "ml", "mt", "gv", "mi", "mr", "mas", "mzn", "mer", "mgo", "mn", "mfe", "mua", "naq", "ne", "nnh", "jgo", "nd", "lrc", "se", "no", "nn", "nus", "ny", "nyn", "or", "om", "os", "ps", "fa", "pl", "pt", "pt-BR", "pt-PT", "prg", "pa", "qu", "ro", "rm", "rof", "rn", "ru", "rwk", "sah", "saq", "sm", "sg", "sbp", "gd", "seh", "sr", "ksb", "sn", "ii", "sd", "si", "sk", "sl", "xog", "so", "st", "es", "es-ES", "es-419", "es-MX", "zgh", "su", "sw", "sv", "gsw", "shi", "dav", "tg", "ta", "twq", "tt", "te", "teo", "th", "bo", "ti", "to", "tr", "tk", "uk", "hsb", "ur", "ug", "uz", "vai", "vi", "vun", "wae", "cy", "fy", "wo", "yav", "yi", "yo", "dje", "zu" ], "enumTitles": [ "Afrikaans", "Aghem", "Akan", "shqip — Albanian", "አማርኛ — Amharic", "العربية — Arabic", "հայերեն — Armenian", "অসমীয়া — Assamese", "asturianu — Asturian", "Kipare — Asu", "azərbaycan — Azerbaijani", "rikpa — Bafia", "bamanakan — Bambara", "বাংলা — Bangla", "Ɓàsàa — Basaa", "euskara — Basque", "беларуская — Belarusian", "Ichibemba — Bemba", "Hibena — Bena", "बड़ो — Bodo", "bosanski — Bosnian", "brezhoneg — Breton", "български — Bulgarian", "မြန်မာ — Burmese", "粵語 — Cantonese", "català — Catalan", "Cebuano", "Tamaziɣt n laṭlaṣ — Central Atlas Tamazight", "کوردیی ناوەندی — Central Kurdish", "𑄌𑄋𑄴𑄟𑄳𑄦 — Chakma", "нохчийн — Chechen", "ᏣᎳᎩ — Cherokee", "Rukiga — Chiga", "中文 — Chinese", "简体中文 — Simplified Chinese", "繁體中文 — Traditional Chinese", "Kölsch — Colognian", "kernewek — Cornish", "Corsican", "hrvatski — Croatian", "čeština — Czech", "dansk — Danish", "duálá — Duala", "Nederlands — Dutch", "རྫོང་ཁ — Dzongkha", "Kĩembu — Embu", "English", "American English", "British English", "esperanto — Esperanto", "eesti — Estonian", "Eʋegbe — Ewe", "ewondo — Ewondo", "føroyskt — Faroese", "Filipino", "suomi — Finnish", "français — French", "français canadien — Canadian French", "furlan — Friulian", "Pulaar — Fulah", "galego — Galician", "Luganda — Ganda", "ქართული — Georgian", "Deutsch — German", "Ελληνικά — Greek", "ગુજરાતી — Gujarati", "Ekegusii — Gusii", "Haitian Creole", "Hausa", "ʻŌlelo Hawaiʻi — Hawaiian", "עברית — Hebrew", "हिन्दी — Hindi", "Hmong", "magyar — Hungarian", "íslenska — Icelandic", "Igbo", "anarâškielâ — Inari Sami", "Indonesia — Indonesian", "Gaeilge — Irish", "italiano — Italian", "日本語 — Japanese", "Javanese", "joola — Jola-Fonyi", "kabuverdianu — Kabuverdianu", "Taqbaylit — Kabyle", "kakɔ — Kako", "kalaallisut — Kalaallisut", "Kalenjin", "Kikamba — Kamba", "ಕನ್ನಡ — Kannada", "کٲشُر — Kashmiri", "қазақ тілі — Kazakh", "ខ្មែរ — Khmer", "Gikuyu — Kikuyu", "Kinyarwanda", "कोंकणी — Konkani", "한국어 — Korean", "Koyra ciini — Koyra Chiini", "Koyraboro senni — Koyraboro Senni", "Kurdish", "Kwasio", "кыргызча — Kyrgyz", "Lakȟólʼiyapi — Lakota", "Kɨlaangi — Langi", "ລາວ — Lao", "Latin", "latviešu — Latvian", "lingála — Lingala", "lietuvių — Lithuanian", "dolnoserbšćina — Lower Sorbian", "Tshiluba — Luba-Katanga", "Dholuo — Luo", "Lëtzebuergesch — Luxembourgish", "Luluhia — Luyia", "македонски — Macedonian", "Kimachame — Machame", "Makua — Makhuwa-Meetto", "Chimakonde — Makonde", "Malagasy", "Melayu — Malay", "മലയാളം — Malayalam", "Malti — Maltese", "Gaelg — Manx", "Maori", "मराठी — Marathi", "Maa — Masai", "مازرونی — Mazanderani", "Kĩmĩrũ — Meru", "metaʼ — Metaʼ", "монгол — Mongolian", "kreol morisien — Morisyen", "MUNDAŊ — Mundang", "Khoekhoegowab — Nama", "नेपाली — Nepali", "Shwóŋò ngiembɔɔn — Ngiemboon", "Ndaꞌa — Ngomba", "isiNdebele — North Ndebele", "لۊری شومالی — Northern Luri", "davvisámegiella — Northern Sami", "norsk bokmål — Norwegian Bokmål", "nynorsk — Norwegian Nynorsk", "Thok Nath — Nuer", "Nyanja", "Runyankore — Nyankole", "ଓଡ଼ିଆ — Odia", "Oromoo — Oromo", "ирон — Ossetic", "پښتو — Pashto", "فارسی — Persian", "polski — Polish", "português — Portuguese", "português — Brazilian Portuguese", "português europeu — European Portuguese", "prūsiskan — Prussian", "ਪੰਜਾਬੀ — Punjabi", "Runasimi — Quechua", "română — Romanian", "rumantsch — Romansh", "Kihorombo — Rombo", "Ikirundi — Rundi", "русский — Russian", "Kiruwa — Rwa", "саха тыла — Sakha", "Kisampur — Samburu", "Samoan", "Sängö — Sango", "Ishisangu — Sangu", "Gàidhlig — Scottish Gaelic", "sena — Sena", "српски — Serbian", "Kishambaa — Shambala", "chiShona — Shona", "ꆈꌠꉙ — Sichuan Yi", "سنڌي — Sindhi", "සිංහල — Sinhala", "slovenčina — Slovak", "slovenščina — Slovenian", "Olusoga — Soga", "Soomaali — Somali", "Southern Sotho", "español — Spanish", "español de España — European Spanish", "español latinoamericano — Latin American Spanish", "español de México — Mexican Spanish", "ⵜⴰⵎⴰⵣⵉⵖⵜ — Standard Moroccan Tamazight", "Sundanese", "Kiswahili — Swahili", "svenska — Swedish", "Schwiizertüütsch — Swiss German", "ⵜⴰⵛⵍⵃⵉⵜ — Tachelhit", "Kitaita — Taita", "тоҷикӣ — Tajik", "தமிழ் — Tamil", "Tasawaq senni — Tasawaq", "татар — Tatar", "తెలుగు — Telugu", "Kiteso — Teso", "ไทย — Thai", "བོད་སྐད་ — Tibetan", "ትግርኛ — Tigrinya", "lea fakatonga — Tongan", "Türkçe — Turkish", "Türkmen dili — Turkmen", "українська — Ukrainian", "hornjoserbšćina — Upper Sorbian", "اردو — Urdu", "ئۇيغۇرچە — Uyghur", "o‘zbek — Uzbek", "ꕙꔤ — Vai", "Tiếng Việt — Vietnamese", "Kyivunjo — Vunjo", "Walser", "Cymraeg — Welsh", "Frysk — Western Frisian", "Wolof", "nuasue — Yangben", "ייִדיש — Yiddish", "Èdè Yorùbá — Yoruba", "Zarmaciine — Zarma", "isiZulu — Zulu" ] }, "default": [] }, "allLanguages": { "title": "Every language a video has", "type": "boolean", "description": "A record for each language the video has captions in, each one transcript: a dubbed video can have a dozen. Languages is ignored when this is on.", "default": false }, "subtitleFormats": { "title": "Subtitle files", "type": "array", "description": "Also give each transcript as SRT or WebVTT text in the record (srt, vtt), ready to save as a subtitle file. The plain text and the timed lines are always there.", "items": { "type": "string", "enum": [ "srt", "vtt" ], "enumTitles": [ "SRT", "WebVTT" ] }, "default": [] }, "maxVideos": { "title": "Videos per channel or playlist", "minimum": 0, "type": "integer", "description": "How many videos each channel or playlist contributes: a channel's newest first, a playlist's in its order (with Published since, counted before the older ones are left out); 0 reads every video. Videos given by link or ID are always read.", "default": 50 }, "dateFrom": { "title": "Published since", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Only a channel's or playlist's videos published on or after this day: a date, or a span back from today such as 30 days. A channel's list stops at its first older video. Videos given by link or ID are read whatever their date." } } }, "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 } } } } } } } } } }