{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper — captions to Markdown", "description": "Get YouTube video transcripts as clean Markdown and timed segments. Accepts video, channel and playlist URLs, picks your preferred caption language with automatic fallback, and returns title, channel, publish date, duration, word count and a per-video status. Failed videos are never charged.", "version": "0.1", "x-build-id": "KFcUY4CdXGuFKVkB1" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/fre.d~youtube-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-fre.d-youtube-transcript", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/fre.d~youtube-transcript/runs": { "post": { "operationId": "runs-sync-fre.d-youtube-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/fre.d~youtube-transcript/run-sync": { "post": { "operationId": "run-sync-fre.d-youtube-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "videoUrls" ], "properties": { "videoUrls": { "title": "Video, channel or playlist URLs", "minItems": 1, "uniqueItems": true, "type": "array", "description": "YouTube video URLs (watch, youtu.be, shorts, embed, live), bare 11-character video IDs, channel URLs (/@handle, /channel/UC..., /c/..., /user/...) or playlist URLs (playlist?list=...). Channels and playlists are expanded into their videos (newest first, up to maxVideosPerChannel). One output record is produced per video.", "items": { "type": "string" } }, "languages": { "title": "Preferred caption languages", "type": "array", "description": "BCP-47 language codes in order of preference, e.g. [\"en\", \"ja\"]. For each language the Actor first looks for a manually created caption track, then for an auto-generated one. If none of the preferred languages exists, it falls back to any manual track and finally to any auto-generated track. The chosen track is reported in the 'language' and 'isAutoGenerated' fields.", "items": { "type": "string" } }, "outputFormat": { "title": "Output format", "enum": [ "markdown", "segments", "both" ], "type": "string", "description": "'markdown' returns the paragraph-formatted transcript only; 'segments' returns the raw timed segments only; 'both' returns both fields.", "default": "both" }, "includeTimestamps": { "title": "Include timestamps in transcript", "type": "boolean", "description": "Prefix every paragraph of the Markdown transcript with its start time, e.g. [12:34]. Segments always carry exact start times regardless of this setting.", "default": false }, "maxVideosPerChannel": { "title": "Max videos per channel / playlist", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Upper bound on how many videos are taken from each channel or playlist URL (newest first for channels). Does not affect video URLs passed directly.", "default": 50 }, "maxConcurrency": { "title": "Max concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many videos are processed in parallel. Each parallel worker uses its own proxy session.", "default": 5 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "YouTube blocks most datacenter IP ranges, so Apify residential proxies are used by default. You can switch to datacenter proxies, your own proxies, or no proxy, but expect more 'failed' records in that case." } } }, "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 }, "PROXY_UNBLOCKER_UNITS": { "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 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }