{ "openapi": "3.0.1", "info": { "title": "Transcribe | Transcribe any video or audio", "description": "Transcribe any video or audio from YouTube, TikTok, Instagram, Twitter, and 1000+ sites", "version": "0.0", "x-build-id": "2eI2a0R0Fq2lKi0pk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/rexreus~Transcribe/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-rexreus-Transcribe", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/rexreus~Transcribe/runs": { "post": { "operationId": "runs-sync-rexreus-Transcribe", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/rexreus~Transcribe/run-sync": { "post": { "operationId": "run-sync-rexreus-Transcribe", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "urls" ], "properties": { "urls": { "title": "Video/Audio URLs", "minItems": 1, "type": "array", "description": "List of video or audio URLs to transcribe.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "directMediaUrls": { "title": "Direct media file URLs (optional)", "type": "array", "description": "Direct links to audio/video files (MP3, MP4, WAV, M4A, WEBM, OGG, FLAC). Bypasses yt-dlp extraction." }, "provider": { "title": "Provider", "enum": [ "openai", "groq", "assemblyai", "deepgram" ], "type": "string", "description": "Select the transcription provider.", "default": "openai" }, "model": { "title": "Model", "enum": [ "whisper-1", "gpt-4o-transcribe", "gpt-4o-mini-transcribe", "whisper-large-v3", "whisper-large-v3-turbo", "universal-3-pro", "universal-2", "nova-3", "nova-2" ], "type": "string", "description": "Select the transcription model. Models vary by accuracy, speed, language support, and output format support.", "default": "whisper-1" }, "openaiApiKey": { "title": "OpenAI API Key", "type": "string", "description": "Your OpenAI API key (starts with 'sk-...'). Required if provider is OpenAI." }, "groqApiKey": { "title": "Groq API Key", "type": "string", "description": "Your Groq API key. Required if provider is Groq. Get free at console.groq.com." }, "assemblyaiApiKey": { "title": "AssemblyAI API Key", "type": "string", "description": "Your AssemblyAI API key. Required if provider is AssemblyAI." }, "deepgramApiKey": { "title": "Deepgram API Key", "type": "string", "description": "Your Deepgram API key. Required if provider is Deepgram." }, "outputFormats": { "title": "Output formats", "minItems": 1, "uniqueItems": true, "type": "array", "description": "Select output formats. SRT/VTT require timestamp support (available with OpenAI whisper-1, AssemblyAI, and Deepgram).", "items": { "type": "string", "enum": [ "json", "srt", "vtt", "txt" ], "enumTitles": [ "JSON (full metadata + segments)", "SRT (subtitle file)", "VTT (web subtitle)", "TXT (plain text)" ] }, "default": [ "json" ] }, "language": { "title": "Source language (optional)", "type": "string", "description": "ISO-639-1 language code (e.g., 'en', 'id', 'ja'). Improves accuracy and speed. Leave empty for auto-detection." }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Translate non-English audio to English. Only works with OpenAI whisper-1 and Groq whisper-large-v3.", "default": false }, "prompt": { "title": "Context prompt (optional)", "maxLength": 1000, "type": "string", "description": "Guide the transcription with context — proper nouns, technical terms, vocabulary. Max 244 tokens. Supported by OpenAI and Groq." }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Apify residential proxy is auto-enabled for YouTube extraction to bypass bot detection. No manual configuration needed." }, "youtubeCookies": { "title": "YouTube Cookies (Optional)", "type": "string", "description": "Optional: Netscape-format YouTube cookies for higher reliability. Not required — residential proxy handles most cases automatically." }, "audioFormat": { "title": "Extracted audio format", "enum": [ "mp3", "m4a", "wav", "webm", "flac" ], "type": "string", "description": "Audio format for extraction. MP3 is recommended for best compatibility.", "default": "mp3" }, "maxDurationMinutes": { "title": "Max video duration", "minimum": 0, "maximum": 1440, "type": "integer", "description": "Skip videos longer than this. Set to 0 for no limit.", "default": 0 }, "speakerDiarization": { "title": "Speaker diarization (AssemblyAI/Deepgram only)", "type": "boolean", "description": "Identify different speakers in the audio. Adds speaker labels to JSON output. Only supported by AssemblyAI and Deepgram.", "default": false }, "debugMode": { "title": "Debug mode", "type": "boolean", "description": "Enable verbose logging with detailed extraction, compression, and API call information.", "default": false } } }, "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 } } } } } } } } } }