{ "openapi": "3.0.1", "info": { "title": "Media Transcriber: Audio & Video to Text, SRT, VTT (Whisper)", "description": "Transcribe or translate your own audio and video files (MP3, WAV, M4A, MP4, MOV, WebM...) into text, timestamped segments, SRT and VTT subtitles. Built-in Whisper models on Apify, or bring your own Groq/OpenAI key for the cheapest per-minute price. Pay only per transcribed minute.", "version": "0.1", "x-build-id": "KGLjGcTTUUefwR9Ea" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/blackcatforge~media-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-blackcatforge-media-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/blackcatforge~media-transcriber/runs": { "post": { "operationId": "runs-sync-blackcatforge-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/blackcatforge~media-transcriber/run-sync": { "post": { "operationId": "run-sync-blackcatforge-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "required": [ "mediaUrls" ], "properties": { "mediaUrls": { "title": "Audio / video file URLs", "type": "array", "description": "Direct links to media files you own or have rights to (your storage bucket, CDN, podcast RSS enclosure, Dropbox/Drive direct-download links). Links to YouTube, TikTok, Instagram, Spotify, Vimeo and similar platforms are refused because their terms forbid downloading.", "items": { "type": "string" } }, "model": { "title": "Built-in model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Base = fast and cheap, good for clear speech (fast-model price). Tiny = fastest, lower accuracy (same price). Small = more accurate for accents, noise and non-English (accurate-model price). Ignored when you bring your own key.", "default": "base" }, "language": { "title": "Language (optional)", "type": "string", "description": "ISO code such as en, es, de, ja. Leave empty to auto-detect." }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe in the original language, or translate speech to English.", "default": "transcribe" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "What to include in each result.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments (JSON)", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments", "srt", "vtt" ] }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Adds per-word timing to segments (slightly slower).", "default": false }, "byokProvider": { "title": "Bring your own key (optional)", "enum": [ "none", "groq", "openai" ], "type": "string", "description": "Use your own Groq (whisper-large-v3-turbo) or OpenAI (whisper-1) account for transcription. You pay the provider directly; this Actor then charges only the low audio-minute-byok price.", "default": "none" }, "apiKey": { "title": "Provider API key", "type": "string", "description": "Stored encrypted by Apify; never logged or saved to results." }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer files are transcribed up to this length (and billed only for that).", "default": 240 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 4096, "type": "integer", "description": "Downloads larger than this are refused. Files above 3 MB per audio minute (typically high-bitrate video) incur the small large-file fee per extra 100 MB; send audio-only files to avoid it.", "default": 1024 } } }, "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 } } } } } } } } } }