{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript & AI Summary Extractor", "description": "Extract YouTube transcripts (timestamped, multi-language, SRT/VTT/CSV/TXT export), expand channels/playlists, and generate AI summaries with topic-based chapters. Proxy-aware with auto anti-block retries.", "version": "0.3", "x-build-id": "qg3cOblSl1mGweHQA" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/kind_cordial~youtube-transcript-ai-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-kind_cordial-youtube-transcript-ai-extractor", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/kind_cordial~youtube-transcript-ai-extractor/runs": { "post": { "operationId": "runs-sync-kind_cordial-youtube-transcript-ai-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/kind_cordial~youtube-transcript-ai-extractor/run-sync": { "post": { "operationId": "run-sync-kind_cordial-youtube-transcript-ai-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 watch URLs, Shorts URLs, video IDs, OR channel/playlist URLs (channel pages, @handles, or ?list= playlist links). Channels/playlists are expanded to their videos automatically (capped by maxVideos).", "items": { "type": "string" } }, "mode": { "title": "Fetch mode", "enum": [ "direct" ], "type": "string", "description": "Direct mode only. Browser/auto modes were removed in 0.3.", "default": "direct" }, "maxVideos": { "title": "Max videos", "minimum": 1, "maximum": 200, "type": "integer", "description": "Maximum number of videos to process in one run (across all URLs and expanded channels/playlists).", "default": 1 }, "preferredLanguage": { "title": "Preferred transcript language", "type": "string", "description": "Preferred transcript language code (e.g. 'en', 'es', 'hi'). Auto-generated captions are used as fallback when this language is unavailable. Defaults to 'en' when omitted.", "default": "en" }, "languages": { "title": "Preferred transcript languages (legacy)", "type": "array", "description": "DEPRECATED in favor of preferredLanguage, kept for backward compatibility. Used only when preferredLanguage is omitted. Ordered list of language codes.", "items": { "type": "string" }, "default": [ "en", "en-US", "en-GB", "a.en" ] }, "languagesExtended": { "title": "Extended fallback languages", "type": "array", "description": "Additional fallback language codes used when preferred language is unavailable. Defaults to the preferred language when omitted.", "items": { "type": "string" } }, "includeRawTranscript": { "title": "Include raw transcript", "type": "boolean", "description": "Return timestamped segments and full text in output. Default true.", "default": true }, "includeSummary": { "title": "Include AI summary", "type": "boolean", "description": "Generate an optional AI summary when a transcript is available. Requires an OpenAI-compatible API key (OPENAI_API_KEY + OPENAI_BASE_URL).", "default": false }, "summaryModel": { "title": "Summary model", "type": "string", "description": "Model name used for optional summarization and chapter segmentation.", "default": "gpt-4o-mini" }, "summaryLength": { "title": "Summary length", "enum": [ "short", "medium", "long" ], "type": "string", "description": "AI summary length. short = 3-5 bullets, medium = 5-8, long = 8-12.", "default": "medium" }, "summaryLanguage": { "title": "Summary language", "type": "string", "description": "Language for the AI summary, independent of the transcript language (e.g. 'es', 'fr'). Leave empty for the model default (usually matches transcript)." }, "enableChapters": { "title": "Enable chapter segmentation", "type": "boolean", "description": "Use AI to group the transcript into topic-based chapters with title + start/end times. Requires includeSummary + an OpenAI-compatible key.", "default": false }, "outputFormat": { "title": "Export format", "enum": [ "json", "srt", "vtt", "csv", "txt" ], "type": "string", "description": "Output format. json = full structured dataset row (default). srt/vtt/csv/txt = also attach a formatted transcript string to the row (srt, vtt, csv, or txt text file body).", "default": "json" }, "maxRetries": { "title": "Max retries (anti-block)", "minimum": 0, "maximum": 10, "type": "integer", "description": "Number of exponential-backoff retries when YouTube returns a block/IP-ban (429-style) error. Each retry rotates the proxy when one is configured.", "default": 3 }, "maxTranscriptLength": { "title": "Max transcript length", "minimum": 1000, "maximum": 50000, "type": "integer", "description": "Truncate transcript text/segments after this many characters.", "default": 15000 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Proxy for transcript fetching and channel/playlist expansion. Defaults to Apify RESIDENTIAL proxies (YouTube blocks datacenter IPs, so residential is required for reliable bulk/channel runs). Set useApifyProxy:true + apifyProxyGroups:[\"RESIDENTIAL\"], or supply your own proxyUrl. Leave empty to use the residential default.", "default": { "useApifyProxy": true, "apifyProxyGroups": [ "RESIDENTIAL" ] } } } }, "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 } } } } } } } } } }