{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber: Whisper Speech to Text, SRT", "description": "Transcribe direct audio and video file URLs (MP3, M4A, WAV, MP4, WebM, OGG) to text with open-source Whisper. Auto language detection, timestamped segments, SRT, VTT and TXT subtitles. Pay per audio minute, failed files are free.", "version": "0.1", "x-build-id": "f9l7BeaMaWxqfs0Ld" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ctriolab~media-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ctriolab-media-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ctriolab~media-transcriber/runs": { "post": { "operationId": "runs-sync-ctriolab-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ctriolab~media-transcriber/run-sync": { "post": { "operationId": "run-sync-ctriolab-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "mediaUrls": { "title": "Media file URLs", "minItems": 1, "type": "array", "description": "Direct links to audio or video files (MP3, M4A, WAV, FLAC, OGG, OPUS, MP4, MOV, WebM, MKV). The URL must return the file itself. Pages of YouTube, TikTok, Instagram and similar platforms are not supported. Leave empty to transcribe a short public domain sample.", "items": { "type": "string" } }, "keyValueStore": { "title": "Apify key-value store with files (optional)", "type": "string", "description": "A key-value store in your Apify account that holds audio or video files. Pick it here and list the record keys below." }, "keyValueStoreKeys": { "title": "Record keys in that store", "type": "array", "description": "Keys of the media records to transcribe, for example interview.mp3.", "items": { "type": "string" } }, "model": { "title": "Whisper model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "tiny is fastest, small is most accurate. base is a good balance for clear speech. All models detect the language automatically.", "default": "base" }, "language": { "title": "Language (optional)", "type": "string", "description": "ISO 639-1 code such as en, de, es, ko, ja. Leave empty to detect the language automatically for each file." }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "transcribe keeps the original language. translate returns English text for speech in any language.", "default": "transcribe" }, "subtitleFormats": { "title": "Subtitle files", "type": "array", "description": "Also save SRT, VTT or plain TXT files to the run's key-value store. Each dataset item gets a link to its files.", "items": { "type": "string", "enum": [ "srt", "vtt", "txt" ], "enumTitles": [ "SRT", "WebVTT", "Plain text" ] }, "default": [] }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add the list of segments with start and end seconds to each dataset item.", "default": true }, "skipSilence": { "title": "Skip silence (voice activity detection)", "type": "boolean", "description": "Skip long silent parts. Faster and reduces made-up text in silence. Billing still uses the full file length.", "default": true }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 500 }, "maxDurationMinutes": { "title": "Max length per file (minutes)", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer files are skipped and not charged.", "default": 240 }, "onlyNew": { "title": "Only new files", "type": "boolean", "description": "Skip URLs this Actor already transcribed in an earlier run with the same monitor name. Useful for scheduled runs over a podcast file list.", "default": false }, "stateName": { "title": "Monitor name", "type": "string", "description": "Name of the key-value store that remembers transcribed URLs when \"Only new files\" is on. Use a different name per list.", "default": "media-transcriber-state" } } }, "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 } } } } } } } } } }