{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber — Speech to Text, SRT/VTT, Podcasts", "description": "Transcribe any audio or video file link, or the newest episodes of a podcast feed: text with timestamps, SRT and WebVTT. 99 languages, auto-detected; translation to English; word timestamps. Whisper runs inside the Actor: no API key, and a file without speech or that cannot be read is never charged.", "version": "1.0", "x-build-id": "G3n16jRef6UjQBCDW" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/steadyscrape~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-steadyscrape-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/steadyscrape~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-steadyscrape-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/steadyscrape~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-steadyscrape-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mediaUrls": { "title": "Audio or video file links", "type": "array", "description": "Direct links to files: mp3, m4a, wav, flac, ogg, opus, aac, mp4, mov, webm, mkv and anything else FFmpeg decodes. A link that opens a web page (YouTube, a share page) is not a file and comes back as a free row that says so.", "items": { "type": "string" } }, "podcastFeeds": { "title": "Podcast feeds", "type": "array", "description": "RSS or Atom feed links, or Apple Podcasts show links (https://podcasts.apple.com/…/id123456789), which are resolved to the show's public feed. The newest episodes of each are transcribed.", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many of the newest episodes of each feed to transcribe.", "default": 1 }, "onlyNewEpisodes": { "title": "Only episodes not delivered before (monitor)", "type": "boolean", "description": "Remembers the episodes this Actor delivered to you and skips them in later runs. Put it on a schedule to transcribe every new episode once, and pay for it once.", "default": false }, "quality": { "title": "Quality", "enum": [ "fast", "balanced", "best" ], "type": "string", "description": "fast: Whisper base, about 8× real time per 4 GB of memory, fine for clear speech. balanced: Whisper small, about 2.4×, good in most languages. best: Whisper large-v3-turbo, about 1.2×, the most accurate, for accents, noise and proper names. Each is charged at its own price per audio minute.", "default": "balanced" }, "language": { "title": "Language", "type": "string", "description": "\"auto\" detects it from the first 90 seconds. Give a code (en, es, de, fr, pt, it, nl, ja, zh, ar, hi, ru… any of Whisper's 99) when you know it: it avoids a wrong guess on files that open with music or another language.", "default": "auto" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Whisper writes the transcript in English instead of the spoken language, in the same pass. Not available with quality \"best\".", "default": false }, "wordTimestamps": { "title": "Word timestamps", "type": "boolean", "description": "Start, end and confidence of every word, inside each segment. Takes longer.", "default": false }, "includeSubtitles": { "title": "Include SRT and WebVTT", "type": "boolean", "description": "Each row carries the subtitles ready to save as .srt and .vtt. Turn it off to make rows smaller.", "default": true }, "maxMinutesPerFile": { "title": "Minutes per file", "minimum": 0, "type": "integer", "description": "Reads only the first minutes of each file; 0 reads the whole file. A file cut short says so in its row.", "default": 0 } } }, "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 } } } } } } } } } }