{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper: Captions & Subtitles for AI", "description": "Get YouTube transcripts (captions/subtitles) as plain text, timestamped segments, SRT or VTT, with video metadata, for videos, Shorts, channels and playlists. Language preference, auto-caption fallback and translation. No speech-to-text. $2.25 per 1,000 transcripts.", "version": "0.1", "x-build-id": "z219XlGRygLuaptk2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cprussin~youtube-transcripts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cprussin-youtube-transcripts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cprussin~youtube-transcripts/runs": { "post": { "operationId": "runs-sync-cprussin-youtube-transcripts", "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/cprussin~youtube-transcripts/run-sync": { "post": { "operationId": "run-sync-cprussin-youtube-transcripts", "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": [ "urls" ], "properties": { "urls": { "title": "YouTube URLs or video IDs", "type": "array", "description": "Video URLs (watch, youtu.be, Shorts, live, embed) or 11-character video IDs. Channel URLs (@handle, /channel/UC…, add /videos, /shorts or /streams to pick a tab) and playlist URLs are expanded into their videos.", "default": [ "https://www.youtube.com/watch?v=UF8uR6Z6KLc", "https://youtu.be/dQw4w9WgXcQ" ], "items": { "type": "string" } }, "maxVideosPerSource": { "title": "Max videos per channel or playlist", "minimum": 1, "maximum": 5000, "type": "integer", "description": "How many of the newest videos to take from each channel or playlist URL. Individual video URLs are always included.", "default": 20 }, "languages": { "title": "Preferred languages", "type": "array", "description": "Caption languages in order of preference, as ISO codes (en, es, pt-BR, …). For each language, human-made captions are preferred over auto-generated ones.", "default": [ "en" ], "items": { "type": "string" } }, "allowAutoGenerated": { "title": "Allow auto-generated captions", "type": "boolean", "description": "Use YouTube's automatic (speech recognition) captions when no human-made captions exist in a preferred language.", "default": true }, "fallbackToAnyLanguage": { "title": "Fall back to any available language", "type": "boolean", "description": "If no preferred language exists, return the video's default caption track instead of an error.", "default": true }, "translateTo": { "title": "Translate to", "type": "string", "description": "Optional language code (e.g. en, es, de). If the video has no captions in this language, YouTube's machine translation of the best track is returned." }, "formats": { "title": "Output formats", "type": "array", "description": "What to include for each video: plain text (`transcript`), timestamped `segments`, and/or ready-to-use `srt` / `vtt` subtitle files.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments" ] }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Add channel, publish date, duration, views, likes, category, keywords, description and thumbnail to each item.", "default": true }, "onlyNew": { "title": "Only new videos (monitoring)", "type": "boolean", "description": "Return only videos whose transcript was not returned by an earlier run with the same URLs and languages. Add channel or playlist URLs and schedule the actor (e.g. daily) to get transcripts of new uploads: the first run is a baseline, later runs output (and bill) only new videos. Failed videos are retried next run. State is kept in the key-value store \"youtube-transcripts-state\" in your account.", "default": false }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "YouTube blocks many datacenter IPs, so residential proxies are the default and recommended. Proxy costs are included in the price.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 20, "type": "integer", "description": "Videos fetched in parallel.", "default": 5 } } }, "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 } } } } } } } } } }