{ "openapi": "3.0.1", "info": { "title": "Audio & Video to Text - Whisper Transcription, SRT, VTT", "description": "Transcribe audio and video files to text with Whisper: full transcript, timed segments, SRT and VTT subtitles, auto language detection, optional English translation and RAG chunks. Direct file links or uploads. $0.008 per minute (fast), $0.014 (accurate); failed files free.", "version": "0.1", "x-build-id": "OCTL16BtuhS0apvzb" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sipki~media-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sipki-media-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/sipki~media-to-text/runs": { "post": { "operationId": "runs-sync-sipki-media-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/sipki~media-to-text/run-sync": { "post": { "operationId": "run-sync-sipki-media-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": { "mediaUrls": { "title": "Media file URLs", "type": "array", "description": "DIRECT links to audio or video files (mp3, m4a, wav, ogg, flac, mp4, mov, webm ...), http/https, one per line. The server must answer with an audio/* or video/* Content-Type. Links to YouTube, TikTok, Instagram, Facebook, X, Vimeo, Spotify, Loom and similar platforms are refused (free), because their terms forbid downloading.", "items": { "type": "string" } }, "keyValueStoreKeys": { "title": "Files in a key-value store", "type": "array", "description": "Keys of audio/video files you uploaded to a key-value store. Combine with 'Media file URLs' freely.", "items": { "type": "string" } }, "keyValueStoreName": { "title": "Key-value store name", "type": "string", "description": "Name of the store that holds the keys above. Leave empty to use this run's default store." }, "mode": { "title": "Quality mode", "enum": [ "fast", "accurate" ], "type": "string", "description": "fast: Whisper base model, quickest and cheapest per minute. accurate: Whisper small model with beam search, fewer errors on accents, noise and names.", "default": "fast" }, "language": { "title": "Language", "type": "string", "description": "'auto' detects the language from the first 30 seconds. Or give a Whisper language code such as en, de, fr, es, it, pt, ru, uk, pl, nl, tr, ar, hi, ja, ko, zh. A fixed language is more reliable for short or noisy files.", "default": "auto" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Whisper's built-in translation: the transcript is returned in English whatever the spoken language.", "default": false }, "includeSubtitles": { "title": "Include SRT and VTT", "type": "boolean", "description": "Add 'srt' and 'vtt' fields with ready-to-use subtitle files.", "default": true }, "vadFilter": { "title": "Skip silence (voice activity detection)", "type": "boolean", "description": "Removes long silences before transcription: fewer made-up words in quiet parts, usually faster. Switch off for music-heavy files with quiet speech.", "default": true }, "chunkSize": { "title": "RAG chunk size (characters)", "minimum": 0, "maximum": 20000, "type": "integer", "description": "0 = no chunks. Otherwise adds a 'chunks' array of about this many characters, cut on segment boundaries, each with its start and end time in seconds.", "default": 0 }, "chunkOverlap": { "title": "Chunk overlap (characters)", "minimum": 0, "maximum": 5000, "type": "integer", "description": "How much of the previous chunk is repeated at the start of the next one (segment granularity).", "default": 100 }, "extractKeyframes": { "title": "Extract key frames (video)", "type": "boolean", "description": "For video files: save up to 'Max key frames' scene-change frames as JPEG to the run's key-value store and list them in 'keyframes' with their time. Included in the price.", "default": false }, "maxKeyframes": { "title": "Max key frames per file", "minimum": 1, "maximum": 50, "type": "integer", "description": "Upper limit of key frames per video.", "default": 12 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 500, "type": "integer", "description": "Larger files are reported as failed (free). Hard limit 500 MB.", "default": 500 }, "maxDurationMinutes": { "title": "Max duration per file (minutes)", "minimum": 1, "maximum": 180, "type": "integer", "description": "Longer files are reported as failed (free). Hard limit 180 minutes.", "default": 180 }, "maxFiles": { "title": "Max files", "minimum": 1, "maximum": 200, "type": "integer", "description": "Files after this number are not processed.", "default": 200 } } }, "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 } } } } } } } } } }