{
"openapi": "3.0.1",
"info": {
"title": "Whisper Transcriber: Audio, Video & Podcast Speech to Text",
"description": "Transcribe audio and video files or podcast RSS feeds with Whisper: full text, timestamped segments, SRT and VTT subtitles, language detection and RAG chunks. Direct file URLs or uploads (not YouTube links). New-episodes mode. No API key. From $0.008 per audio minute.",
"version": "0.1",
"x-build-id": "bQRl7drSVjT5gRj6V"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/cprussin~media-transcriber/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-cprussin-media-transcriber",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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/cprussin~media-transcriber/runs": {
"post": {
"operationId": "runs-sync-cprussin-media-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/cprussin~media-transcriber/run-sync": {
"post": {
"operationId": "run-sync-cprussin-media-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 and video URLs",
"type": "array",
"description": "Direct links to audio or video files (MP3, M4A, WAV, OGG, OPUS, FLAC, MP4, MOV, MKV, WEBM and anything else FFmpeg reads), one per line. Apify key-value store record URLs are read with your token. YouTube, TikTok and Instagram page links are not supported. Billed per started minute of audio; failed files are free.",
"items": {
"type": "string"
}
},
"startUrls": {
"title": "Start URLs",
"type": "array",
"description": "Optional alternative to Audio and video URLs, in Apify's request-list format (e.g. a file with one URL per line, or the output of another actor). Combined with Audio and video URLs.",
"items": {
"type": "object",
"required": [
"url"
],
"properties": {
"url": {
"type": "string",
"title": "URL of a web page",
"format": "uri"
}
}
}
},
"keyValueStoreRecords": {
"title": "Key-value store records",
"type": "array",
"description": "Files uploaded to an Apify key-value store, as storeId/recordKey or username~store-name/recordKey, one per line. Use this to transcribe your own recordings without hosting them anywhere.",
"items": {
"type": "string"
}
},
"rssFeeds": {
"title": "Podcast RSS feeds",
"type": "array",
"description": "Podcast RSS (or Atom) feed URLs, one per line. The newest episodes of each feed are transcribed (see Max episodes per feed).",
"items": {
"type": "string"
}
},
"maxEpisodes": {
"title": "Max episodes per feed",
"minimum": 1,
"maximum": 500,
"type": "integer",
"description": "How many of each feed's newest episodes to consider. With Only new episodes, those already transcribed by an earlier run are skipped.",
"default": 5
},
"onlyNewEpisodes": {
"title": "Only new episodes (monitoring)",
"type": "boolean",
"description": "Skip episodes transcribed by an earlier run with the same feeds. Schedule the actor (e.g. daily) to transcribe each new episode once. Failed episodes are retried next run. State is kept in the key-value store \"media-transcriber-state\" in your account.",
"default": false
},
"model": {
"title": "Whisper model",
"enum": [
"base",
"small"
],
"type": "string",
"description": "Base: fast and cheap, good for clear speech ($0.008/min). Small: more accurate on accents, noise, names and non-English audio ($0.016/min, about 3x slower).",
"default": "base"
},
"language": {
"title": "Language",
"enum": [
"auto",
"af",
"sq",
"am",
"ar",
"hy",
"as",
"az",
"ba",
"eu",
"be",
"bn",
"bs",
"br",
"bg",
"my",
"yue",
"ca",
"zh",
"hr",
"cs",
"da",
"nl",
"en",
"et",
"fo",
"fi",
"fr",
"gl",
"ka",
"de",
"el",
"gu",
"ht",
"ha",
"haw",
"he",
"hi",
"hu",
"is",
"id",
"it",
"ja",
"jw",
"kn",
"kk",
"km",
"ko",
"lo",
"la",
"lv",
"ln",
"lt",
"lb",
"mk",
"mg",
"ms",
"ml",
"mt",
"mi",
"mr",
"mn",
"ne",
"no",
"nn",
"oc",
"ps",
"fa",
"pl",
"pt",
"pa",
"ro",
"ru",
"sa",
"sr",
"sn",
"sd",
"si",
"sk",
"sl",
"so",
"es",
"su",
"sw",
"sv",
"tl",
"tg",
"ta",
"tt",
"te",
"th",
"bo",
"tr",
"tk",
"uk",
"ur",
"uz",
"vi",
"cy",
"yi",
"yo"
],
"type": "string",
"description": "Spoken language. Auto-detect works well for one language per file; set it for short clips, strong accents or to force a language.",
"default": "auto"
},
"outputFormat": {
"title": "Output format",
"enum": [
"transcript",
"chunks"
],
"type": "string",
"description": "Transcript: one item per file with the full text and timestamped segments. RAG chunks: one item per chunk of about the chosen size, with start and end times, ready for a vector database. SRT and VTT subtitle files are saved and linked in both.",
"default": "transcript"
},
"chunkSize": {
"title": "Chunk size (characters)",
"minimum": 200,
"maximum": 20000,
"type": "integer",
"description": "RAG chunks only. Maximum characters per chunk, overlap included. Chunks break between transcript segments. About 4 characters make one token.",
"default": 1500
},
"chunkOverlap": {
"title": "Chunk overlap (characters)",
"minimum": 0,
"maximum": 10000,
"type": "integer",
"description": "RAG chunks only. Up to this many characters of whole segments repeated from the end of the previous chunk, at most half the chunk size. 0 for none.",
"default": 150
},
"maxDurationMinutes": {
"title": "Max duration per file (minutes)",
"minimum": 1,
"maximum": 300,
"type": "integer",
"description": "Longer files are skipped with an error (free). Caps cost per file. At most 300.",
"default": 180
},
"maxFileSizeMb": {
"title": "Max file size (MB)",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Larger downloads are skipped with an error (free). Video files are large: the audio track is all that is used.",
"default": 1000
},
"timeoutSecs": {
"title": "Download timeout (seconds)",
"minimum": 10,
"maximum": 3600,
"type": "integer",
"description": "Max time to download one file.",
"default": 600
}
}
},
"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
}
}
}
}
}
}
}
}
}
}