{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Captions, Subtitles & RAG API", "description": "Extract YouTube transcripts, captions, subtitles, timestamps, metadata, SRT, WebVTT, Markdown, and RAG-ready chunks from videos, Shorts, channels, and playlists. Works with bulk URLs and residential proxy support.", "version": "0.1", "x-build-id": "OstFbPovspWr6B7ZJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/meilimiao~yt-transcript-captions-api/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-meilimiao-yt-transcript-captions-api", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/meilimiao~yt-transcript-captions-api/runs": { "post": { "operationId": "runs-sync-meilimiao-yt-transcript-captions-api", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/meilimiao~yt-transcript-captions-api/run-sync": { "post": { "operationId": "run-sync-meilimiao-yt-transcript-captions-api", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "YouTube video URLs, Shorts URLs, playlist URLs, channel URLs, or raw 11-character video IDs. Start with a single video to test, then scale to bulk URLs.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "json", "text", "srt", "vtt", "markdown" ], "type": "string", "description": "Choose how transcript text is formatted in formattedTranscript. JSON keeps structured fields only.", "default": "json" }, "languages": { "title": "Language priority", "type": "array", "description": "Language codes in priority order. The Actor tries manual captions first, then auto-generated captions.", "default": [ "en", "es", "ko" ], "items": { "type": "string" } }, "translateTo": { "title": "Translate to language", "type": "string", "description": "Optional target language code, e.g. es, fr, de, zh. Uses YouTube built-in translation when available." }, "includeMetadata": { "title": "Include video metadata", "type": "boolean", "description": "Include title, channel, duration, views, publish date, thumbnail, description, and tags when available.", "default": true }, "includeTimestamps": { "title": "Include timestamped segments", "type": "boolean", "description": "Include per-caption segments with start time, duration, and text.", "default": true }, "includeAvailableLanguages": { "title": "Include available languages", "type": "boolean", "description": "Return all transcript languages available on the video.", "default": true }, "includeRagChunks": { "title": "Include RAG chunks", "type": "boolean", "description": "Split transcript into chunks suitable for vector databases and RAG pipelines.", "default": false }, "chunkSize": { "title": "RAG chunk size", "minimum": 200, "maximum": 8000, "type": "integer", "description": "Approximate max characters per RAG chunk.", "default": 1000 }, "maxVideos": { "title": "Maximum videos", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Limit total videos processed, useful for channels and playlists.", "default": 100 }, "maxConcurrency": { "title": "Concurrency", "minimum": 1, "maximum": 25, "type": "integer", "description": "How many videos to process in parallel. Default 2 is recommended for YouTube reliability; increase carefully for large proxy-backed runs.", "default": 2 }, "fallbackToAnyLanguage": { "title": "Fallback to any language", "type": "boolean", "description": "If requested languages are unavailable, use any available transcript instead of failing.", "default": true }, "preserveFormatting": { "title": "Preserve caption formatting", "type": "boolean", "description": "Keep supported HTML formatting tags from YouTube captions.", "default": false }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Recommended: Apify Proxy with RESIDENTIAL group and US country. YouTube often blocks datacenter IPs, especially for bulk transcript extraction.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ], "apifyProxyCountry": "US" } } } }, "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 } } } } } } } } } }