{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber: Speech to Text, SRT, VTT (Whisper)", "description": "Transcribe audio and video files to text with Whisper: MP3, M4A, WAV, MP4, WebM and more from direct links, podcast RSS feeds or another Actor's dataset. Timestamped segments, SRT and VTT subtitles, 99 languages, optional translation to English. Pay per audio minute from $0.003.", "version": "1.0", "x-build-id": "19xJ7BXdIVjgL8Pbs" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/prometheus-maker~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-prometheus-maker-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/prometheus-maker~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-prometheus-maker-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/prometheus-maker~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-prometheus-maker-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", "properties": { "urls": { "title": "Audio or video file URLs", "type": "array", "description": "Direct links to audio or video files: MP3, M4A, WAV, OGG, OPUS, FLAC, MP4, MOV, WebM, MKV and more. Public links only (YouTube and other video pages are not supported; give the file itself).", "items": { "type": "string" } }, "podcastFeeds": { "title": "Podcast RSS feeds", "type": "array", "description": "Podcast RSS or Atom feed URLs. The newest episodes of each feed are transcribed (see 'Episodes per feed').", "items": { "type": "string" } }, "episodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many of the newest episodes to transcribe from each feed.", "default": 1 }, "datasetId": { "title": "Dataset with file URLs (from another Actor)", "type": "string", "description": "Transcribe the audio/video URLs found in a dataset, e.g. the 'downloadUrl' field of Bulk File Downloader. Set the field name below." }, "datasetUrlField": { "title": "URL field in that dataset", "type": "string", "description": "Field holding the URL (or a list of URLs). Use dots for nested fields, e.g. 'media.audioUrl'.", "default": "url" }, "model": { "title": "Model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Whisper model size. Bigger = more accurate and slower. 'base' is a good default for clear speech; 'small' handles accents, noise and non-English speech better; 'tiny' is fastest and cheapest. Each has its own price per audio minute.", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "Spoken language as a two-letter code, e.g. 'en', 'de', 'es', 'ja'. Leave empty to detect it automatically from the first 30 seconds. Setting it avoids wrong detection on files that start with music.", "default": "" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Output an English translation instead of a transcript in the original language. Same price.", "default": false }, "vocabularyHint": { "title": "Vocabulary hint", "type": "string", "description": "Optional names and terms that appear in the audio, e.g. 'Apify, Kubernetes, Dr. Nakamura'. Helps the model spell them right." }, "skipSilence": { "title": "Skip silence", "type": "boolean", "description": "Skip long silent parts and music before recognizing speech (voice activity detection). Faster and fewer made-up words in silent parts. Billing is by file length either way.", "default": true }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add the list of segments (start, end in seconds, text) to each row. The SRT and VTT files are saved either way.", "default": true }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer files are transcribed only up to this point, and charged only for that part.", "default": 240 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Larger files are skipped and not charged.", "default": 1000 } } }, "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 } } } } } } } } } }