{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — Channels, Playlists & AI Chunks", "description": "Extract YouTube transcripts and subtitles in bulk from videos, Shorts, whole channels, playlists or search results. Plain text, timestamped segments, SRT/VTT and RAG-ready chunks with deep links. Pay only for transcripts delivered.", "version": "0.2", "x-build-id": "3tClC5U8EPo9VMZgZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cleancut~youtube-transcript-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cleancut-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/cleancut~youtube-transcript-scraper/runs": { "post": { "operationId": "runs-sync-cleancut-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/cleancut~youtube-transcript-scraper/run-sync": { "post": { "operationId": "run-sync-cleancut-youtube-transcript-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "startUrls": { "title": "YouTube URLs or IDs", "type": "array", "description": "Videos (watch, youtu.be, Shorts, live, embed, mobile), channels (@handle, /channel/UC…, /c/…, /user/…) and playlists. Plain video IDs and @handles work too.", "items": { "type": "string" } }, "searchQueries": { "title": "Search terms", "type": "array", "description": "One term per line. Each term is searched on YouTube and its top videos are transcribed (how many is set in “Channel, playlist & search options”).", "items": { "type": "string" } }, "maxVideosPerSource": { "title": "Max videos per channel, playlist or search", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Newest first for channels. Use a small number to test, a large one to transcribe a whole channel.", "default": 20 }, "channelTabs": { "title": "Channel tabs", "type": "array", "description": "Which channel sections to read videos from.", "items": { "type": "string", "enum": [ "videos", "shorts", "streams" ], "enumTitles": [ "Videos", "Shorts", "Live streams" ] }, "default": [ "videos" ] }, "languages": { "title": "Preferred languages", "type": "array", "description": "Language codes in order of preference (en, es, pt…). “es” also matches regional variants such as “es-419”.", "default": [ "en" ], "items": { "type": "string" } }, "captionType": { "title": "Caption type", "enum": [ "preferManual", "any", "manualOnly", "autoOnly" ], "type": "string", "description": "Which captions to use when a video has both human-made and automatic (speech recognition) captions.", "default": "preferManual" }, "fallbackToAnyLanguage": { "title": "Fall back to any available language", "type": "boolean", "description": "If none of the preferred languages exists, return the best available transcript instead of an error.", "default": true }, "translateTo": { "title": "Translate to (optional)", "type": "string", "description": "Language code to translate the transcript into (es, fr, de…). Leave empty to keep the original language. Tip: run “List caption languages only” first to see which languages each video can be translated to." }, "outputFormats": { "title": "Extra formats", "type": "array", "description": "Pick one or more. AI-ready chunks group the transcript into blocks of N seconds, each with a deep link to that second of the video: ideal for LLMs, embeddings and RAG.", "items": { "type": "string", "enum": [ "segments", "chunks", "srt", "vtt" ], "enumTitles": [ "Timestamped segments", "AI-ready chunks (RAG) with deep links", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "segments" ] }, "chunkDurationSeconds": { "title": "Chunk length (seconds)", "minimum": 10, "maximum": 1800, "type": "integer", "description": "Approximate length of each AI-ready chunk. Only used when “AI-ready chunks” is selected.", "default": 60 }, "includeVideoDetails": { "title": "Include extended video details", "type": "boolean", "description": "Adds publish date, upload date, category, like count, description, keywords, thumbnail and live flag (about half a second more per video). Title, channel, duration and views are always included.", "default": true }, "listLanguagesOnly": { "title": "List caption languages only (free)", "type": "boolean", "description": "Returns one free row per video with its caption tracks (language, human-made or automatic, translatable) and the languages it can be translated to. No transcript is downloaded and nothing is charged.", "default": false }, "maxTotalTranscripts": { "title": "Max transcripts in total", "minimum": 0, "type": "integer", "description": "Stop after this many transcripts (0 = no limit). Useful to cap the cost of a run.", "default": 0 }, "maxConcurrency": { "title": "Parallel videos", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many videos to process at the same time.", "default": 5 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Residential proxy is recommended: YouTube blocks most data-center IPs. Transcripts are tiny (~30 KB per video), so residential traffic costs very little.", "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 } } } } } } } } } }