{ "openapi": "3.0.1", "info": { "title": "Whisper Transcriber — audio & video to text, SRT & VTT", "description": "Transcribe audio/video files or podcast RSS feeds with Whisper inside the Actor — no API key. Full text, timestamped segments, SRT + VTT subtitles, 99+ languages, optional English translation. Pay per minute transcribed; failed or silent files are never billed.", "version": "0.1", "x-build-id": "mxeNGUMbcqgQXtHRl" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/amanatools~whisper-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-amanatools-whisper-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/amanatools~whisper-transcriber/runs": { "post": { "operationId": "runs-sync-amanatools-whisper-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/amanatools~whisper-transcriber/run-sync": { "post": { "operationId": "run-sync-amanatools-whisper-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": [ "media_urls" ], "properties": { "media_urls": { "title": "Media URLs", "type": "array", "description": "Audio/video file URLs (mp3, m4a, wav, ogg, flac, mp4, webm, …) or podcast RSS feed URLs — feeds expand to their latest episodes. Up to 25 URLs per run. Note: social-platform pages (YouTube, TikTok, …) are not supported — send direct media files you have the right to process.", "items": { "type": "string" } }, "model": { "title": "Model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Bigger models are more accurate and slower. 'base' is the sweet spot for clear speech; use 'small' for noisy audio, heavy accents or hard languages ('small' downloads on first use, adding ~1 minute once per run).", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "ISO code like 'en', 'ar', 'es', 'ru' — or 'auto' to detect. Setting it explicitly is slightly faster and more reliable for short clips.", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "'Transcribe' keeps the original language. 'Translate' produces English text regardless of the spoken language.", "default": "transcribe" }, "rss_episodes": { "title": "Episodes per RSS feed", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many of the newest episodes to transcribe from each feed URL.", "default": 1 }, "max_minutes_per_file": { "title": "Max minutes per file", "minimum": 1, "maximum": 480, "type": "integer", "description": "Hard cap on transcribed audio per file — this is also your cost ceiling: max spend per file = $0.005 + $0.008 x this number. Longer files are transcribed up to the cap and flagged 'truncated'.", "default": 120 }, "vad_filter": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Voice-activity detection skips silent stretches — faster and fewer hallucinated captions on quiet audio. Turn off only if speech is being missed.", "default": true }, "word_timestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add per-word start/end times inside each segment. Slower; needed only for karaoke-style captions or precise alignment.", "default": false }, "include_failed_files": { "title": "Include failed files in output", "type": "boolean", "description": "If enabled, files that fail to download or decode still appear in the dataset with their status and error.", "default": true } } }, "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 } } } } } } } } } }