{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper + Whisper AI Fallback", "description": "Extract YouTube transcripts from any video — even without captions. Whisper AI fallback, LLM-ready output, SRT/VTT export. No API key. $0.001/video.", "version": "1.0", "x-build-id": "8ef9DZXchSY32Li9K" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/codepoetry~youtube-transcript-ai-scraper/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-codepoetry-youtube-transcript-ai-scraper", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "YouTube video, playlist, or channel URLs to process. Supports watch URLs, short youtu.be links, playlist URLs, and channel URLs. The prefilled URL is a working demo — click Start to try it.", "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 process from a playlist or channel. Single video URLs ignore this setting. For channels, videos are returned newest first.", "default": 10 }, "languages": { "title": "Caption languages", "type": "array", "description": "Caption languages to try, in order of preference. The first match on the video is used. Add multiple codes to fall back automatically. Common: en, es, fr, de, pt, ja, zh, ko, ar, hi. See the README for all 130+ supported codes.", "default": [ "en" ], "items": { "type": "string" } }, "subType": { "title": "Caption source", "enum": [ "manual", "auto", "both" ], "type": "string", "description": "Which type of YouTube captions to use. Manual = human-written or uploaded by the creator. Auto = YouTube's machine-generated captions. Both (prefer manual) tries manual first, then auto. Most videos only have auto-generated captions.", "default": "both" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Choose which transcript formats to include. Plain Text is simplest — one block of words. JSON includes timestamps for each segment. LLM-Ready strips [Music], (laughter), and other filler — ideal for AI pipelines. SRT and VTT are standard subtitle formats for video editors and players.", "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. Only available for auto-generated captions and AI transcriptions — not manual captions.", "default": false }, "forceWhisperLanguage": { "title": "AI transcription language (optional)", "type": "string", "description": "Force the AI model to a specific language, skipping auto-detection (~20% faster). Use when you know the channel's language. Leave empty to auto-detect. Not the same as Caption Languages — that selects YouTube's existing captions. See the README for all 99 supported language codes." }, "maxAiMinutes": { "title": "Max AI minutes per run", "minimum": 0, "type": "integer", "description": "Hard cap on total AI transcription minutes for this run. When the cap is reached, remaining videos without captions are skipped with an error — the run continues for other videos. Set to 0 for unlimited. Recommended: set a cap when processing an unknown playlist or channel to avoid unexpected costs.", "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 and you only want the shorter ones. 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 } } } } } } } } } }