{ "openapi": "3.0.1", "info": { "title": "Audio and Video Transcript (OpenAI Whisper)", "description": "This Actor transcribes audio or video files from publicly accessible URLs using OpenAI's Whisper API. To use this Actor, you'll need to provide your own OpenAI API key. It supports multiple languages and highly customizable parameters, enabling precise control over the transcription process.", "version": "0.0", "x-build-id": "jArUsI47cymuDRrs3" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/vittuhy~audio-and-video-transcript/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-vittuhy-audio-and-video-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/vittuhy~audio-and-video-transcript/runs": { "post": { "operationId": "runs-sync-vittuhy-audio-and-video-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/vittuhy~audio-and-video-transcript/run-sync": { "post": { "operationId": "run-sync-vittuhy-audio-and-video-transcript", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "url", "openai_api_key" ], "properties": { "url": { "title": "File URL", "type": "array", "description": "Publicly accessible URL(s) of the audio/video file(s). Each file must be 25 MB or smaller (OpenAI Whisper limit).", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "language": { "title": "Language", "enum": [ "Auto-detect", "Afrikaans", "Albanian", "Amharic", "Arabic", "Armenian", "Assamese", "Azerbaijani", "Bashkir", "Basque", "Belarusian", "Bengali", "Bosnian", "Breton", "Bulgarian", "Burmese", "Catalan", "Chinese", "Croatian", "Czech", "Danish", "Dutch", "English", "Esperanto", "Estonian", "Faroese", "Finnish", "French", "Galician", "Georgian", "German", "Greek", "Gujarati", "Haitian Creole", "Hausa", "Hawaiian", "Hebrew", "Hindi", "Hungarian", "Icelandic", "Indonesian", "Italian", "Japanese", "Javanese", "Kannada", "Kazakh", "Khmer", "Korean", "Lao", "Latin", "Latvian", "Lithuanian", "Luxembourgish", "Macedonian", "Malagasy", "Malay", "Malayalam", "Maltese", "Maori", "Marathi", "Mongolian", "Nepali", "Norwegian", "Norwegian Nynorsk", "Occitan", "Pashto", "Persian", "Polish", "Portuguese", "Punjabi", "Romanian", "Russian", "Sanskrit", "Serbian", "Shona", "Sindhi", "Sinhala", "Slovak", "Slovenian", "Somali", "Spanish", "Sundanese", "Swahili", "Swedish", "Tagalog", "Tajik", "Tamil", "Tatar", "Telugu", "Thai", "Turkish", "Turkmen", "Ukrainian", "Urdu", "Uzbek", "Vietnamese", "Welsh", "Yiddish", "Yoruba" ], "type": "string", "description": "Select the language of the audio. Choose 'Auto-detect' to let Whisper determine the language automatically.", "default": "Auto-detect" }, "response_format": { "title": "Response Format", "enum": [ "text", "srt", "vtt", "json", "verbose_json" ], "type": "string", "description": "How the transcript should be formatted. Choose 'verbose_json' to enable timestamps.", "default": "text" }, "timestamp_granularity": { "title": "Timestamp Granularity", "enum": [ "none", "segment", "word" ], "type": "string", "description": "Timestamp detail level. Only applies when 'response_format' is 'verbose_json'.", "default": "none" }, "temperature": { "title": "Temperature", "pattern": "^(0(\\.[0-9]+)?|1(\\.0+)?)$", "type": "string", "description": "Sampling temperature, between 0 and 1. Higher values make output more random.", "default": "0.0" }, "prompt": { "title": "Prompt", "type": "string", "description": "Optional text to guide the model's style or correct names/spellings. Must match the audio language.", "default": "" }, "openai_api_key": { "title": "OpenAI API Key", "type": "string", "description": "Your secret OpenAI API key." } } }, "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 } } } } } } } } } }