{
"openapi": "3.0.1",
"info": {
"title": "Speech to Text",
"description": "Transcribe audio and video files to text with timecodes, in 90+ languages. Whisper large v3 with nothing to set up, optional translation to English, SRT and WebVTT subtitles, and chunks for RAG. Export data, run via API, schedule runs, or integrate with AI workflows.",
"version": "0.1",
"x-build-id": "mfZ6eS8BxFpy92czz"
},
"servers": [
{
"url": "https://api.apify.com/v2"
}
],
"paths": {
"/acts/lergassy~speech-to-text/run-sync-get-dataset-items": {
"post": {
"operationId": "run-sync-get-dataset-items-lergassy-speech-to-text",
"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": {
"$ref": "#/components/schemas/inputSchema"
}
}
}
},
"parameters": [
{
"name": "token",
"in": "query",
"required": true,
"schema": {
"type": "string"
},
"description": "Enter your Apify token here"
}
],
"responses": {
"200": {
"description": "OK"
}
}
}
},
"/acts/lergassy~speech-to-text/runs": {
"post": {
"operationId": "runs-sync-lergassy-speech-to-text",
"x-openai-isConsequential": false,
"summary": "Executes an Actor and returns information about the initiated run in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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": {
"$ref": "#/components/schemas/runsResponseSchema"
}
}
}
}
}
}
},
"/acts/lergassy~speech-to-text/run-sync": {
"post": {
"operationId": "run-sync-lergassy-speech-to-text",
"x-openai-isConsequential": false,
"summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
"tags": [
"Run Actor"
],
"requestBody": {
"required": true,
"content": {
"application/json": {
"schema": {
"$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 URLs",
"type": "array",
"description": "Direct links to media files: MP3, M4A, WAV, FLAC, OGG, MP4, MOV, WEBM and anything else ffmpeg can read. Video files are stripped to their audio track automatically.",
"items": {
"type": "string"
}
},
"file": {
"title": "📎 Upload a file",
"type": "string",
"description": "Upload one audio or video file from your computer instead of giving a URL."
},
"quality": {
"title": "🎚️ Recognition quality",
"enum": [
"fast",
"accurate"
],
"type": "string",
"description": "Fast is the everyday choice. Accurate makes fewer mistakes on accents, noise and technical vocabulary, and costs more.",
"default": "fast"
},
"language": {
"title": "🔤 Spoken language",
"type": "string",
"description": "Two-letter code of the language spoken, for example en, ru, id. Leave empty to detect it automatically."
},
"translateToEnglish": {
"title": "Translate to English",
"type": "boolean",
"description": "Return an English transcript no matter what language is spoken.",
"default": false
},
"diarize": {
"title": "🗣️ Speaker labels ($)",
"type": "boolean",
"description": "Mark who is speaking in each part of the recording. Every segment gets a speaker (\"Speaker 1\", \"Speaker 2\", …), the transcript is laid out as a conversation, and subtitles carry the names. Charged per minute on top of the transcription, and slow: the speaker model runs on the machine, so expect several minutes of processing per hour of audio, while a plain transcript is near-instant.",
"default": false
},
"speakerCount": {
"title": "Number of speakers",
"minimum": 1,
"maximum": 20,
"type": "integer",
"description": "How many people talk in the recording. Leave empty and the Actor works it out on its own; set it when you already know, for example two people in an interview."
},
"vocabularyHint": {
"title": "Vocabulary hint",
"type": "string",
"description": "Names, jargon or spellings that appear in the audio, comma separated. Helps the engine get proper nouns right."
},
"includeSegments": {
"title": "Timed segments",
"type": "boolean",
"description": "Return every recognised passage with its start time and duration, alongside the full transcript.",
"default": true
},
"chunkForRag": {
"title": "Split into RAG chunks",
"type": "boolean",
"description": "Split the transcript into retrieval chunks that keep the timecode where each one starts.",
"default": false
},
"chunkSize": {
"title": "Chunk size (characters)",
"minimum": 200,
"maximum": 20000,
"type": "integer",
"description": "Target size of one chunk. Chunks break on sentence ends, so real sizes vary.",
"default": 1200
},
"chunkOverlapSeconds": {
"title": "Chunk overlap (seconds)",
"minimum": 0,
"maximum": 60,
"type": "integer",
"description": "How many seconds of the previous chunk to repeat at the start of the next one.",
"default": 0
},
"subtitleFormat": {
"title": "Subtitle file",
"enum": [
"none",
"srt",
"vtt"
],
"type": "string",
"description": "Also return a ready-made subtitle file as text.",
"default": "none"
},
"apiKey": {
"title": "🔑 Your own Groq API key ($)",
"type": "string",
"description": "Optional. Supply your own key and the per-minute price drops sharply; you then pay Groq directly for the recognition. Leave empty to use the built-in key with nothing to set up."
},
"maxConcurrency": {
"title": "⚡ Max concurrency",
"minimum": 1,
"maximum": 10,
"type": "integer",
"description": "How many files to transcribe at the same time.",
"default": 3
},
"maxFileSizeMb": {
"title": "📦 Max file size (MB)",
"minimum": 1,
"maximum": 2000,
"type": "integer",
"description": "Files larger than this are skipped with an error row instead of being downloaded.",
"default": 500
},
"timeoutPerFileSecs": {
"title": "⏱️ Timeout per file (seconds)",
"minimum": 30,
"maximum": 3600,
"type": "integer",
"description": "How long one file may take to download and recognise before it is given up on.",
"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
}
}
},
"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
}
}
}
}
}
}
}
}
}
}