{
"openapi": "3.0.1",
"info": {
"title": "Audio & Video Transcription (Whisper) for AI Agents",
"description": "Transcribe your audio and video files with Whisper: text, timestamped segments, optional word timings, language detection, translation to English, and SRT/VTT subtitle files. MP3, M4A, WAV, MP4, WebM and more from URLs or key-value stores. Priced per audio minute.",
"version": "1.0",
"x-build-id": "dwOoUTm9N9hhIE0af"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/tinplatelabs~transcriber/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-tinplatelabs-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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/tinplatelabs~transcriber/runs": {
"post": {
"operationId": "runs-sync-tinplatelabs-transcriber",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/tinplatelabs~transcriber/run-sync": {
"post": {
"operationId": "run-sync-tinplatelabs-transcriber",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": [
"media"
],
"properties": {
"media": {
"title": "Audio or video files",
"type": "array",
"description": "Files to transcribe, one per line: direct http(s) URLs of audio or video files, files in a key-value store as kvs://KEY (the store picked below, or this run's store) or kvs://STORE_ID_OR_NAME/KEY, or signed Apify record URLs (with ?signature=). MP3, M4A/AAC, WAV, FLAC, OGG/Opus, WebM, MP4, MOV, MKV and more. Links to YouTube, TikTok, Instagram, Vimeo, Spotify and other platform pages are not supported. Up to 200 files per run, 1 GB each.",
"items": {
"type": "string"
}
},
"keyValueStoreId": {
"title": "Key-value store",
"type": "string",
"description": "Your key-value store that holds the media files. Pick it (or paste its ID) and list its records as kvs://KEY. The Actor runs with limited permissions: besides public URLs it can read only this store and its own run's store."
},
"model": {
"title": "Model",
"enum": [
"base",
"small",
"medium"
],
"type": "string",
"description": "Whisper model size. base is fast and good for clear speech; small is more accurate on accents, noise and non-English speech; medium is the most accurate and slowest (needs 4 GB memory). Each has its own per-minute price.",
"default": "base"
},
"language": {
"title": "Language",
"type": "string",
"description": "Spoken language as an ISO 639-1 code (e.g. en, es, de, ja). Leave empty to detect it automatically (reported with a confidence). Setting it avoids misdetection on short or noisy clips."
},
"task": {
"title": "Task",
"enum": [
"transcribe",
"translate"
],
"type": "string",
"description": "transcribe writes what is said in its own language; translate writes an English translation.",
"default": "transcribe"
},
"wordTimestamps": {
"title": "Word timestamps",
"type": "boolean",
"description": "Add each word with its start, end and probability to every segment. Slightly slower.",
"default": false
},
"vadFilter": {
"title": "Skip silence (VAD)",
"type": "boolean",
"description": "Detect speech with Silero VAD and skip silence and music. Faster and avoids invented text in silent parts. Turn off only if quiet speech is being dropped.",
"default": true
},
"initialPrompt": {
"title": "Vocabulary hint",
"type": "string",
"description": "Optional text that guides spelling and style: names, product terms, acronyms that appear in the recording (up to 800 characters)."
},
"includeSegments": {
"title": "Include segments",
"type": "boolean",
"description": "Add segments (start, end, text) to each result. Turn off for long files when you only need the text and subtitle files.",
"default": true
},
"saveSubtitleFiles": {
"title": "Save SRT, VTT and TXT files",
"type": "boolean",
"description": "Save subtitles (SRT, WebVTT) and the plain text to the run's key-value store and link them in files.",
"default": true
},
"maxDurationMinutes": {
"title": "Maximum duration per file (minutes)",
"minimum": 1,
"maximum": 300,
"type": "integer",
"description": "Longer files get a TOO_LONG error item and are not charged (1-300).",
"default": 180
},
"fileTimeoutSecs": {
"title": "Timeout per file (seconds)",
"minimum": 60,
"maximum": 14400,
"type": "integer",
"description": "A file that takes longer to transcribe gets a TIMEOUT error item and is not charged (60-14400).",
"default": 3600
}
}
},
"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
}
}
}
}
}
}
}
}
}
}