{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber (Whisper): Speech to Text, SRT, VTT", "description": "Transcribe audio and video files from direct links, or a podcast RSS feed, to text, SRT, WebVTT and JSON with timestamps. Speech to text by an open Whisper model inside the run, so audio is not sent to an outside AI service. Language auto-detect and a max-minutes limit.", "version": "0.1", "x-build-id": "ZS4srKBsom1Qb62zv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/madrasco~audio-podcast-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-madrasco-audio-podcast-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/madrasco~audio-podcast-transcriber/runs": { "post": { "operationId": "runs-sync-madrasco-audio-podcast-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/madrasco~audio-podcast-transcriber/run-sync": { "post": { "operationId": "run-sync-madrasco-audio-podcast-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "audioUrls": { "title": "Audio or video file URLs", "type": "array", "description": "Direct links to audio or video files (MP3, M4A, WAV, OGG, FLAC, MP4, WebM...). The link must download the file itself, not open a web page. YouTube, TikTok and Instagram links are refused because their terms don't allow downloading.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "rssUrl": { "title": "Podcast RSS feed URL", "type": "string", "description": "A podcast's RSS feed. The newest episodes (up to 'Max episodes') are transcribed." }, "maxEpisodes": { "title": "Max episodes from the feed", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many of the newest feed episodes to transcribe.", "default": 3 }, "maxMinutes": { "title": "Max audio minutes per run", "minimum": 0, "type": "integer", "description": "The run never starts a file that would take the total transcribed audio past this many minutes; such files get a 'skipped' row. 0 = no limit.", "default": 60 }, "language": { "title": "Language", "type": "string", "description": "Two-letter language code (e.g. 'en', 'de', 'es'). Leave empty to detect it automatically from the first 30 seconds.", "default": "" }, "beamSize": { "title": "Accuracy mode", "enum": [ "5", "1" ], "type": "string", "description": "5 = beam search (default, more accurate); 1 = greedy (faster).", "default": "5" }, "vadFilter": { "title": "Skip silence (voice activity detection)", "type": "boolean", "description": "Remove long silent stretches before transcribing. Can be faster on recordings with pauses.", "default": false }, "speakerLabels": { "title": "Label speakers (Speaker 1, Speaker 2...)", "type": "boolean", "description": "Split the transcript by speaker and label each part with an anonymous 'Speaker 1', 'Speaker 2'... (who spoke when; no names, nobody is identified). Runs inside the run, so the audio still never leaves it. Adds processing time. Measured on English recordings only.", "default": false } } }, "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 } } } } } } } } } }