{ "openapi": "3.0.1", "info": { "title": "Audio & Video to Text — Transcription, SRT, VTT & RAG chunks", "description": "Transcribe your audio and video files (MP3, M4A, WAV, WhatsApp voice notes, MP4, MOV...) into text with timestamps, SRT/VTT subtitles, Markdown and RAG-ready chunks. Open-source Whisper runs inside Apify: no third-party API. Strong in Spanish, 90+ languages. From $0.004 per audio minute.", "version": "0.0", "x-build-id": "u2aHdKG8ZvBbOXgaX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/lif_manager~audio-video-transcription/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-lif_manager-audio-video-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/lif_manager~audio-video-transcription/runs": { "post": { "operationId": "runs-sync-lif_manager-audio-video-transcription", "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/lif_manager~audio-video-transcription/run-sync": { "post": { "operationId": "run-sync-lif_manager-audio-video-transcription", "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": { "files": { "title": "Audio or video files (files or URLs)", "type": "array", "description": "Upload files or paste direct public URLs to audio/video files. Formats: MP3, WAV, M4A, AAC, OGG, OPUS (WhatsApp voice notes), FLAC, WEBM, MP4, MOV, MKV, AVI, WMA, AMR, 3GP. Up to 500 MB per file. If you upload files here, also select the storage they went to below. Leave empty to see a demo." }, "storage": { "title": "Storage with uploaded files", "type": "string", "description": "The key-value store where your uploaded files are. This Actor runs with limited permissions and can only read the storage you pick here. If you leave the list above empty, every audio/video file in this storage is transcribed." }, "mode": { "title": "Quality", "enum": [ "accurate", "fast" ], "type": "string", "description": "Accurate: Whisper 'small' model, good punctuation and names ($0.010 per audio minute). Fast: Whisper 'base' model, cheaper drafts with more mistakes ($0.004 per audio minute).", "default": "accurate" }, "language": { "title": "Language", "enum": [ "auto", "es", "en", "pt", "fr", "de", "it", "ca", "gl", "eu", "nl", "pl", "ru", "uk", "tr", "ar", "hi", "ja", "ko", "zh" ], "type": "string", "description": "Spoken language. Auto-detect works well; set it when the audio starts with music or with another language.", "default": "auto" }, "vocabulary": { "title": "Names and terms (optional)", "type": "string", "description": "Names, brands or technical terms that appear in the audio, separated by commas. Helps spell them right, e.g. 'Mercado Pago, ARCA, Rosario, Dr. Fernández'." }, "output_mode": { "title": "Output: one item per", "enum": [ "transcript", "segments", "chunks" ], "type": "string", "description": "transcript: one item per file with text, timestamped segments and chunks. segments: one item per timestamped segment. chunks: one item per chunk, ready for a vector database.", "default": "transcript" }, "chunk_tokens": { "title": "Chunk size (tokens, approx.)", "minimum": 0, "maximum": 4000, "type": "integer", "description": "Target chunk size, estimated as 4 characters per token. Chunks never cut a sentence segment and keep their start and end time. 0 = no chunks.", "default": 400 }, "chunk_overlap": { "title": "Chunk overlap (tokens, approx.)", "minimum": 0, "maximum": 500, "type": "integer", "description": "Last segments of a chunk repeated at the start of the next one.", "default": 40 }, "skip_silence": { "title": "Skip silence and music", "type": "boolean", "description": "Voice activity detection: skips long silences and music, which makes it faster and avoids invented text. You are still billed per audio minute of the file.", "default": true }, "save_files": { "title": "Save SRT, VTT, Markdown and TXT files", "type": "boolean", "description": "Saves each transcript as .srt, .vtt, .md and .txt in the run's key-value store, with download links in the result.", "default": true }, "max_minutes_per_file": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Files longer than this are skipped and not charged (cost control).", "default": 240 } } }, "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 } } } } } } } } } }