{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript API – Captions & AI Transcription", "description": "Extract YouTube transcripts from videos and Shorts using existing captions first, with AI transcription fallback when needed. Supports batch processing, timestamps, SRT, WebVTT, language selection, and video metadata.", "version": "2.0", "x-build-id": "yaFm3LrXz9EAhXgug" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lance_api~youtube-transcripts-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lance_api-youtube-transcripts-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/lance_api~youtube-transcripts-scraper/runs": { "post": { "operationId": "runs-sync-lance_api-youtube-transcripts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/lance_api~youtube-transcripts-scraper/run-sync": { "post": { "operationId": "run-sync-lance_api-youtube-transcripts-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "YouTube URLs", "minItems": 1, "maxItems": 500, "type": "array", "description": "Add up to 500 standard, short, mobile, or Shorts URLs. Duplicate video IDs are processed once.", "default": [ "https://www.youtube.com/watch?v=dQw4w9WgXcQ" ], "items": { "type": "string" } }, "formats": { "title": "Output formats", "type": "array", "description": "Choose only the transcript formats your workflow needs. Fewer formats keep each JSON result smaller and simpler for downstream tools. Text is best for reading/AI; segments add timestamps; SRT and WebVTT are subtitle files.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Text", "Timestamped segments", "SRT", "WebVTT" ] }, "default": [ "text", "segments" ] }, "preferredLanguages": { "title": "Preferred languages", "type": "array", "description": "Optional caption-language priority, for example es then en. Use this when language matters: the Actor tries only these languages in order, with manual captions before auto captions. If none match, it uses AI fallback when enabled; leave empty to accept the best available caption in any language.", "default": [], "items": { "type": "string" } }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "YouTube frequently blocks cloud datacenter IPs. Keep Apify Proxy enabled. If results still return YOUTUBE_BLOCKED, select the RESIDENTIAL proxy group; residential traffic can create additional proxy charges.", "default": { "useApifyProxy": true } }, "enableAiTranscription": { "title": "AI transcription fallback", "type": "boolean", "description": "Choose coverage versus AI budget. When no usable caption is available, AI can transcribe the video's audio; turn this off to use captions only and completely avoid AI transcription charges.", "default": true }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Include title, channel, duration, views, thumbnail, and publishing information. Turn it off when you only need transcript content to keep each JSON result smaller and simpler.", "default": true }, "includeMediaUrls": { "title": "Include media URLs", "type": "boolean", "description": "Include temporary audio and video delivery URLs only when an immediate downstream media task needs them. Keep this off for smaller, cleaner JSON; signed URLs can expire.", "default": false }, "translate": { "title": "Translate YouTube captions", "type": "boolean", "description": "Request YouTube's caption translation when the selected caption track supports it. This does not translate AI transcripts.", "default": false }, "targetLanguage": { "title": "Translation target language", "type": "string", "description": "Language code used only when caption translation is enabled and supported, for example en or es. It does not translate AI transcripts.", "default": "en" }, "maxAiMinutes": { "title": "Maximum AI minutes per run", "minimum": 0, "type": "integer", "description": "Run-wide AI spending guard. Stop starting new AI jobs when their billed minutes would exceed this budget; use 0 only when you intentionally want no run-wide AI limit.", "default": 100 }, "skipAiIfLongerThanMinutes": { "title": "Skip long videos for AI", "minimum": 0, "type": "integer", "description": "Per-video AI spending guard. Skip AI for a captionless video longer than this value, preventing one long podcast or stream from consuming an unexpected share of your budget. Use 0 to disable it.", "default": 60 } } }, "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 } } } } } } } } } }