{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript & Subtitles Scraper API", "description": "Scrape YouTube transcripts, subtitles, and captions in bulk, the cheapest pay-per-video YouTube transcript API on Apify. Callable from any MCP client (Claude, Cursor, ChatGPT). Supports YouTube videos, Shorts, and every URL format.", "version": "0.0", "x-build-id": "65F37GICXtBDE4hxM" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/johnvc~YoutubeTranscripts/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-johnvc-YoutubeTranscripts", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/johnvc~YoutubeTranscripts/runs": { "post": { "operationId": "runs-sync-johnvc-YoutubeTranscripts", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/johnvc~YoutubeTranscripts/run-sync": { "post": { "operationId": "run-sync-johnvc-YoutubeTranscripts", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "youtube_url" ], "properties": { "youtube_url": { "title": "YouTube URL(s)", "description": "REQUIRED. Provide one YouTube URL as a string, or multiple as an array. Works with standard videos, Shorts, youtu.be short links, embed URLs, and m.youtube.com mobile URLs. Each URL is processed in parallel. Invalid URLs are recorded as errors in the dataset but do not stop the run. Charged per video successfully transcribed." }, "languages": { "title": "Preferred Languages", "type": "array", "description": "Ordered list of ISO 639-1 language codes. The first available transcript matching one of these languages is returned. Example: [\"en\", \"es\", \"fr\"] tries English first, then Spanish, then French. Defaults to [\"en\"] when omitted.", "items": { "type": "string" }, "default": [ "en" ] }, "translate_to": { "title": "Translate To", "type": "string", "description": "Optional. If set to an ISO 639-1 code (e.g. \"es\", \"fr\", \"de\"), the picked transcript is translated to this language. Requires the source transcript to be translatable - run with list_only=true first to see translation_languages for each available transcript. If translation is unavailable, the original transcript is returned (no error)." }, "transcript_type": { "title": "Transcript Type", "enum": [ "any", "manual", "generated" ], "type": "string", "description": "Filter which transcript variant to consider when both manually-created and auto-generated captions exist for a language. \"any\" picks whichever matches the language priority first; \"manual\" only considers human-made captions; \"generated\" only considers auto-generated.", "default": "any" }, "output_formats": { "title": "Additional Output Formats", "type": "array", "description": "Optional list of extra output formats to include in the dataset alongside the default structured fields. Allowed values: \"srt\" (SubRip subtitles), \"vtt\" (WebVTT subtitles), \"text\" (plain text, newline-separated). Unknown values are ignored with a warning. The structured fields (timestamped, non_timestamped, etc.) are always included.", "items": { "type": "string" }, "default": [] }, "preserve_formatting": { "title": "Preserve HTML formatting", "type": "boolean", "description": "If true, keep YouTube's inline HTML formatting tags (, ) in transcript text. Default false (strips them for clean text).", "default": false }, "list_only": { "title": "List available transcripts only (discovery mode)", "type": "boolean", "description": "If true, do NOT fetch any transcript. Instead, for each URL return the list of all available transcripts with their language code, generated/manual status, is_translatable flag, and translation_languages. Useful for discovering what languages exist before picking one. Not charged as a videoprocessed event.", "default": false }, "include_metadata": { "title": "Include video metadata", "type": "boolean", "description": "If true, also fetch video metadata via yt-dlp: title, description, channel_name, channel_id, channel_url, view_count, like_count, video_duration_seconds, upload_date, thumbnail_url, tags, categories, availability, was_live. Adds about 1-3 seconds per video. If metadata extraction fails, the transcript is still returned and metadata_error is populated. Defaults to true.", "default": true } } }, "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 } } } } } } } } } }