YouTube Transcript Extractor
Pricing
$3.00/month + usage
Go to Store
YouTube Transcript Extractor
Under maintenance
Extract YouTube transcripts. Perfect for content analysis, research & automation API integration.
0.0 (0)
Pricing
$3.00/month + usage
0
1
1
Last modified
5 days ago
You can access the YouTube Transcript Extractor programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.0", "x-build-id": "CYQOfi3EX7qoP38F8" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/linen_snack~youtube-transcript-subtitles-extractor/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-linen_snack-youtube-transcript-subtitles-extractor", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/linen_snack~youtube-transcript-subtitles-extractor/runs": { "post": { "operationId": "runs-sync-linen_snack-youtube-transcript-subtitles-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/linen_snack~youtube-transcript-subtitles-extractor/run-sync": { "post": { "operationId": "run-sync-linen_snack-youtube-transcript-subtitles-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": [ "videoUrls" ], "properties": { "videoUrls": { "title": "YouTube Video URLs", "minItems": 1, "maxItems": 1000, "type": "array", "description": "List of YouTube video URLs to extract transcripts from. Supports youtube.com/watch and youtu.be formats.", "items": { "type": "string", "pattern": "^https?://(www\\.)?(youtube\\.com/watch\\?v=|youtu\\.be/)[a-zA-Z0-9_-]{11}" } }, "maxConcurrency": { "title": "Max Concurrency", "minimum": 1, "maximum": 10, "type": "integer", "description": "Maximum number of videos to process simultaneously. Higher values increase speed but may trigger rate limiting.", "default": 3 }, "retryAttempts": { "title": "Retry Attempts", "minimum": 0, "maximum": 5, "type": "integer", "description": "Number of retry attempts for failed extractions with exponential backoff.", "default": 3 }, "requestDelay": { "title": "Request Delay (ms)", "minimum": 500, "maximum": 10000, "type": "integer", "description": "Delay between batches in milliseconds to avoid rate limiting.", "default": 1500 }, "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Enable Apify proxy for requests to avoid IP blocking and rate limiting. Recommended for large batches.", "default": true }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Advanced proxy settings for Apify proxy service", "properties": { "useApifyProxy": { "title": "Use Apify Proxy", "type": "boolean", "description": "Use Apify proxy service" }, "apifyProxyGroups": { "title": "Apify Proxy Groups", "type": "array", "items": { "type": "string" }, "description": "Proxy groups to use (e.g., ['RESIDENTIAL'], ['DATACENTER'])" }, "apifyProxyCountry": { "title": "Apify Proxy Country", "type": "string", "description": "Country code for proxy location (e.g., 'US', 'GB', 'DE')" } }, "default": { "useApifyProxy": true, "apifyProxyGroups": [ "DATACENTER" ], "apifyProxyCountry": "US" } }, "includeTimestamps": { "title": "Include Timestamps", "type": "boolean", "description": "Include detailed timestamp information (formatted time strings) in segment data.", "default": true }, "includeFullText": { "title": "Include Full Text", "type": "boolean", "description": "Include concatenated full text transcript in addition to individual segments.", "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 } } } } } } } } }}YouTube Transcript Extractor OpenAPI definition
OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for YouTube Transcript Extractor from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients:
