{
"openapi": "3.0.1",
"info": {
"title": "Audio & Video Transcriber – Whisper Speech to Text, SRT, VTT",
"description": "Transcribe audio and video files and podcast RSS feeds with Whisper: 99 languages, translation to English, timestamps, SRT/VTT subtitles, word timings and paragraphs. $0.006 per minute.",
"version": "1.0",
"x-build-id": "zRfMcmvrecXvg2h97"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/pinkish_armada~audio-transcriber/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-pinkish_armada-audio-transcriber",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/pinkish_armada~audio-transcriber/runs": {
"post": {
"operationId": "runs-sync-pinkish_armada-audio-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/pinkish_armada~audio-transcriber/run-sync": {
"post": {
"operationId": "run-sync-pinkish_armada-audio-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": [
"mediaUrls"
],
"properties": {
"mediaUrls": {
"title": "Audio/video file URLs or podcast RSS feeds",
"type": "array",
"description": "Direct links to audio or video files (MP3, M4A, WAV, OGG, OPUS, FLAC, MP4, MOV, WEBM, MKV...) or podcast RSS feed URLs (the newest episodes are transcribed). Links to YouTube, TikTok, Instagram, Facebook, X, Vimeo, Spotify or SoundCloud pages are refused because those platforms do not allow automated downloads.",
"items": {
"type": "string"
}
},
"model": {
"title": "Model",
"enum": [
"base",
"small"
],
"type": "string",
"description": "base: fast and cheap, very good for clear English speech. small: noticeably more accurate, especially for accents, noisy audio and non-English languages (priced higher, about 3-4x the compute).",
"default": "base"
},
"language": {
"title": "Language",
"type": "string",
"description": "ISO 639-1 code of the spoken language (e.g. en, de, es, fr, ja). Leave empty to auto-detect.",
"default": ""
},
"task": {
"title": "Task",
"enum": [
"transcribe",
"translate"
],
"type": "string",
"description": "transcribe: text in the spoken language. translate: English translation of non-English speech.",
"default": "transcribe"
},
"maxEpisodesPerFeed": {
"title": "Episodes per podcast feed",
"minimum": 1,
"maximum": 100,
"type": "integer",
"description": "For RSS feed URLs: how many of the newest episodes to transcribe.",
"default": 3
},
"includeSegments": {
"title": "Include timestamped segments",
"type": "boolean",
"description": "Add a segments array (start, end, text) to each result.",
"default": true
},
"saveSubtitles": {
"title": "Save SRT and VTT subtitle files",
"type": "boolean",
"description": "Save .srt and .vtt files to the key-value store and link them from each result (srtUrl, vttUrl).",
"default": true
},
"wordTimestamps": {
"title": "Word-level timestamps",
"type": "boolean",
"description": "Add per-word start/end times and confidence inside each segment (slower).",
"default": false
},
"skipSilence": {
"title": "Skip silence (voice activity detection)",
"type": "boolean",
"description": "Skip long silent or music-only parts before transcribing. Reduces hallucinated text on silence.",
"default": true
},
"maxDurationMinutes": {
"title": "Maximum duration per file (minutes)",
"minimum": 1,
"maximum": 600,
"type": "integer",
"description": "Longer files are skipped with error TOO_LONG and not charged.",
"default": 180
},
"maxFileSizeMb": {
"title": "Maximum file size (MB)",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Larger downloads are stopped with error TOO_LARGE (not charged).",
"default": 500
},
"requestTimeoutSecs": {
"title": "Download timeout (seconds)",
"minimum": 10,
"maximum": 600,
"type": "integer",
"description": "Network timeout for each download request.",
"default": 120
}
}
},
"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
}
}
}
}
}
}
}
}
}
}