{ "openapi": "3.0.1", "info": { "title": "Whisper Audio & Video Transcriber (Speech to Text, SRT/VTT)", "description": "Transcribe audio and video files to text with OpenAI Whisper. 99 languages, auto language detection, timestamps, SRT and VTT subtitles, translation to English. Paste any direct link, Google Drive or Dropbox. From $0.006 per minute.", "version": "1.0", "x-build-id": "sdRE7ABL27eEDK2pz" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/cyuli~whisper-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-cyuli-whisper-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/cyuli~whisper-transcriber/runs": { "post": { "operationId": "runs-sync-cyuli-whisper-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/cyuli~whisper-transcriber/run-sync": { "post": { "operationId": "run-sync-cyuli-whisper-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": [ "audioUrls" ], "properties": { "audioUrls": { "title": "Audio or video URLs", "type": "array", "description": "Direct links to audio or video files (mp3, wav, m4a, aac, ogg, opus, flac, mp4, mov, webm, mkv...). Public Google Drive, Dropbox and OneDrive share links are converted to direct downloads automatically. Each file becomes one dataset item.", "items": { "type": "string" } }, "model": { "title": "Model", "enum": [ "base", "small" ], "type": "string", "description": "\"base\" is fast and cheap, good for clear speech, podcasts and meetings. \"small\" is noticeably more accurate on accents, noise, names and non-English audio.", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "ISO 639-1 code of the spoken language (en, es, pt, fr, de, it, ja, hi...). Leave \"auto\" to detect it automatically. Setting it improves accuracy on short or mixed audio.", "default": "auto" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Output an English translation instead of the original-language transcript.", "default": false }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add the list of segments with start and end times (seconds) to each result.", "default": true }, "includeSubtitles": { "title": "Include SRT and VTT subtitles", "type": "boolean", "description": "Add SRT and VTT subtitles to each result and save .srt, .vtt and .txt files in the run's key-value store with download links.", "default": true }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add start/end times and confidence for every word inside each segment (useful for karaoke-style captions and editing). Slightly slower.", "default": false }, "vadFilter": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Detect and skip silent parts before transcribing. Faster and reduces hallucinated text on music or silence. You are billed for the full file duration either way.", "default": true }, "initialPrompt": { "title": "Vocabulary hint", "type": "string", "description": "Optional text with names, brands or jargon that appear in the audio (e.g. \"Apify, Kubernetes, Dr. Nakamura\"). Helps Whisper spell them correctly." }, "maxDurationMinutes": { "title": "Max duration per file (minutes)", "minimum": 1, "maximum": 1440, "type": "integer", "description": "Files longer than this are skipped without charge. Protects you from accidentally transcribing very long files.", "default": 240 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 8192, "type": "integer", "description": "Files larger than this are skipped without charge.", "default": 2048 } } }, "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 } } } } } } } } } }