{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber (Whisper) - MP3/MP4 to Text, SRT, VTT", "description": "Transcribe audio and video files to text with Whisper in bulk: MP3, M4A, WAV, MP4, podcasts. Timestamps, SRT and VTT subtitles, 99 languages, translate to English. $0.005 per audio minute; failed links and silence are free.", "version": "0.1", "x-build-id": "IEUacWYMRPMGvgTRR" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tinyrex~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tinyrex-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tinyrex~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-tinyrex-audio-video-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/tinyrex~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-tinyrex-audio-video-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": { "mediaUrls": { "title": "Audio or video file URLs", "type": "array", "description": "Direct links to audio or video files you have the rights to transcribe: MP3, M4A, WAV, OGG, OPUS, FLAC, AAC, MP4, MOV, MKV, WEBM and more (anything ffmpeg reads). Podcast episode enclosure URLs from an RSS feed work. YouTube/TikTok/Instagram and other platform page links are not supported. Failed links are listed with the reason and are free.", "items": { "type": "string" } }, "datasetId": { "title": "Read media URLs from a dataset (optional)", "type": "string", "description": "ID of an Apify dataset with media links, e.g. podcast episodes from an RSS scraper. Without a URL field, every value that looks like a link to an audio/video file is collected." }, "urlField": { "title": "URL field in the dataset (optional)", "type": "string", "description": "Dataset field that holds the media link (dot notation like enclosure.url works; arrays are expanded). Use it when your links have no file extension." }, "model": { "title": "Whisper model", "enum": [ "base", "small" ], "type": "string", "description": "Both run OpenAI's open-source Whisper locally (faster-whisper, int8). Small is noticeably better for accents, noisy audio and non-English speech.", "default": "base" }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "es", "de", "fr", "it", "pt", "nl", "pl", "ru", "uk", "tr", "ar", "hi", "ja", "ko", "zh", "id", "vi", "sv", "da", "no", "fi", "cs", "ro", "hu", "el", "he", "hr", "sr" ], "type": "string", "description": "Auto-detect works for 99 languages. Setting the language avoids wrong detections on short or noisy clips.", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "translate = Whisper's built-in speech-to-English translation (same price).", "default": "transcribe" }, "vadFilter": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Voice activity detection removes long silences and music-only parts before transcription. Reduces hallucinated text on silent parts. Billing is by audio length either way.", "default": true }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Adds a segments array (start, end in seconds, text) to each row.", "default": true }, "includeSubtitles": { "title": "Create SRT and VTT subtitle files", "type": "boolean", "description": "Saves .srt and .vtt subtitles to the key-value store and adds srtUrl / vttUrl to each row.", "default": true }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Only the first N minutes of each file are transcribed and billed (truncated = true in the row).", "default": 120 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 2000, "type": "integer", "description": "Bigger files are skipped (free).", "default": 500 }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Hard cap on unique URLs processed in this run.", "default": 100 } } }, "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 } } } } } } } } } }