Audio And Video Transcriber (OpenAI GPT-4o-transcribe)
Pricing
$5.00/month + usage
Go to Store
Audio And Video Transcriber (OpenAI GPT-4o-transcribe)
Downloads videos from public URLs, extracts audio, and transcribes them using OpenAI
5.0 (1)
Pricing
$5.00/month + usage
0
Total users
1
Monthly users
1
Runs succeeded
>99%
Last modified
4 days ago
You can access the Audio And Video Transcriber (OpenAI GPT-4o-transcribe) programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in Integrations settings in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "aZu7xGrnGTATvcYfm" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/stanvanrooy6~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-stanvanrooy6-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/stanvanrooy6~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-stanvanrooy6-audio-video-transcriber", "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/stanvanrooy6~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-stanvanrooy6-audio-video-transcriber", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "required": [ "video_urls", "openai_api_key" ], "properties": { "video_urls": { "title": "Video URLs", "type": "array", "description": "A list of public direct URLs to video files (e.g., MP4, MOV, AVI). Each URL will be processed individually.", "items": { "type": "string" } }, "openai_api_key": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key for transcription services. This is treated as a secret and stored securely." }, "openai_model": { "title": "OpenAI Transcription Model", "enum": [ "gpt-4o-mini-transcribe", "gpt-4o-transcribe" ], "type": "string", "description": "The OpenAI model for transcription. 'gpt-4o-mini-transcribe' is fast and cost-effective. 'gpt-4o-transcribe' may offer higher accuracy.", "default": "gpt-4o-mini-transcribe" }, "openai_transcription_language": { "title": "Audio Language (Optional)", "type": "string", "description": "The language of the audio in ISO-639-1 format (e.g., 'en' for English, 'es' for Spanish). If omitted, OpenAI attempts auto-detection.", "default": "" }, "openai_transcription_prompt": { "title": "Transcription Prompt (Optional)", "type": "string", "description": "An optional text prompt to guide the model's style, vocabulary, or to correct specific words/names. Can significantly improve accuracy for domain-specific content." }, "openai_transcription_temperature": { "title": "Transcription Temperature", "pattern": "^(0(\\.\\d+)?|1(\\.0+)?|[01])$", "type": "string", "description": "Sampling temperature (0.0-1.0). Enter as a string, e.g., \"0.2\". Higher values make output more random; lower make it more deterministic. Default is \"0.0\".", "default": "0.0" }, "max_concurrent_tasks": { "title": "Maximum Concurrent Tasks", "minimum": 1, "type": "integer", "description": "The maximum number of videos to process in parallel. Adjust based on resources and API rate limits.", "default": 5 }, "max_retries": { "title": "Maximum Retries per Video", "minimum": 0, "type": "integer", "description": "Number of times to retry processing a video if an error occurs (e.g., download/API failure).", "default": 3 } } }, "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 } } } } } } } } }}Audio And Video Transcriber (OpenAI GPT-4o-transcribe) 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 Audio And Video Transcriber (OpenAI GPT-4o-transcribe) 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:
![🔍 GPT Search [Private API] avatar](https://images.apifyusercontent.com/81nLWVkp8Qadtbe0Aa_lGKz-r8JgutEL97JUhtGzzoc/rs:fill:76:76/cb:1/aHR0cHM6Ly9hcGlmeS1pbWFnZS11cGxvYWRzLXByb2QuczMudXMtZWFzdC0xLmFtYXpvbmF3cy5jb20vY21lNndpMUFENVJ3T2NQWGEtYWN0b3ItTkJaUEpmVGNWRGJyc2EwOFQtT3ZQZXNqd09yNC1TZWFyY2hfQVBJLTIucG5n.webp){kind=avatar}
