{ "openapi": "3.0.1", "info": { "title": "YouTube Transcript Scraper - Bulk, No Browser", "description": "Transcripts from YouTube videos, playlists and channels, charged only when a transcript is actually delivered. No browser, so a run finishes in seconds. Benchmarked 45/45 videos with zero failures. Every video that cannot be fetched says exactly why instead of disappearing from the output.", "version": "0.2", "x-build-id": "vefkfLBxj7oqyrN6m" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hllerdgn80~youtube-transcript-batch/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hllerdgn80-youtube-transcript-batch", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hllerdgn80~youtube-transcript-batch/runs": { "post": { "operationId": "runs-sync-hllerdgn80-youtube-transcript-batch", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hllerdgn80~youtube-transcript-batch/run-sync": { "post": { "operationId": "run-sync-hllerdgn80-youtube-transcript-batch", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "type": "array", "description": "Videos, playlists or channels, one per line. Video IDs on their own work too. A playlist or channel URL is expanded into its videos automatically.", "items": { "type": "string" } }, "languages": { "title": "Preferred languages", "type": "array", "description": "Two-letter codes in order of preference, e.g. en, es, tr. The first one the video actually has wins; if none is available the video is reported as such rather than returned in another language. Leave empty and the actor follows the language the video is spoken in (falling back to English when YouTube states no language at all).", "items": { "type": "string" } }, "allowAutoGenerated": { "title": "Accept auto-generated captions", "type": "boolean", "description": "Most videos have no human-written transcript. Leave on unless you specifically need manually written captions.", "default": true }, "allowTranslation": { "title": "Translate if the language is missing", "type": "boolean", "description": "If none of your preferred languages exist, ask YouTube to translate an available track into the first one.", "default": true }, "outputFormat": { "title": "Output format", "enum": [ "text", "segments", "srt", "all" ], "type": "string", "description": "Plain text is what you feed an LLM. Segments keep per-line timestamps. SRT is a subtitle file.", "default": "text" }, "includeVideoMetadata": { "title": "Include title, channel and duration", "type": "boolean", "description": "Title, channel and duration come from the same response as the captions, so this costs nothing extra.", "default": true }, "maxVideosPerSource": { "title": "Max videos per playlist or channel", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Applies only to playlist and channel URLs. Single video URLs are never limited.", "default": 50 }, "concurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 30, "type": "integer", "description": "10 is a good balance. Raise it for large batches, lower it if YouTube starts refusing.", "default": 10 }, "proxyConfiguration": { "title": "Proxy", "type": "object", "description": "Leave this as it is. The default is the configuration the published benchmark was measured on; lowering it reduces the success rate.", "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 } } } } } } } } } }