{ "openapi": "3.0.1", "info": { "title": "Audio & Video to Text — AI Transcript API (Whisper)", "description": "Transcribe audio & video to text in bulk with OpenAI Whisper AI. Paste file links, Google Drive/Dropbox or podcast RSS feeds → transcripts with timestamps + SRT/VTT subtitles. 99 languages, auto-detect, translate to English. From $0.006/min, no API key.", "version": "0.1", "x-build-id": "71EOGTkGZs86BOqHJ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/adorable_partial~whisper-audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-adorable_partial-whisper-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/adorable_partial~whisper-audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-adorable_partial-whisper-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/adorable_partial~whisper-audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-adorable_partial-whisper-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 / video URLs", "type": "array", "description": "Direct links to audio or video files (mp3, m4a, wav, ogg, flac, mp4, webm, mov...). Public Google Drive and Dropbox share links are supported.", "items": { "type": "string" } }, "rssFeeds": { "title": "Podcast RSS feeds", "type": "array", "description": "Podcast RSS feed URLs. The newest episodes of each feed are transcribed.", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Max episodes per feed", "minimum": 1, "type": "integer", "description": "How many of the newest episodes to transcribe from each RSS feed.", "default": 1 }, "quality": { "title": "Quality", "enum": [ "fast", "balanced", "accurate" ], "type": "string", "description": "fast = Whisper base (cheapest), balanced = Whisper small, accurate = Whisper large-v3-turbo (best accuracy, slowest).", "default": "balanced" }, "language": { "title": "Language", "type": "string", "description": "ISO 639-1 code of the spoken language (e.g. en, pt, es). Leave empty to auto-detect." }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Output an English translation instead of the original-language transcript.", "default": false }, "includeSegments": { "title": "Include timestamped segments", "type": "boolean", "description": "Add a list of segments with start/end times to each result.", "default": true }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add start/end times for every word inside each segment (great for karaoke-style captions, editing and search). Slightly slower.", "default": false }, "maxDurationMinutes": { "title": "Max duration per file (minutes)", "minimum": 1, "type": "integer", "description": "Only the first N minutes of each file are transcribed. Protects you from unexpectedly long files.", "default": 180 } } }, "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 } } } } } } } } } }