{ "openapi": "3.0.1", "info": { "title": "Audio Transcription: Speech to Text, Video, Podcast | $0.01/min", "description": "Speech to text with Whisper: transcribe audio and video files and podcast episodes, with timestamps and SRT or VTT subtitles. Paste MP3, M4A, WAV, MP4 or other media links, or podcast RSS feeds for their newest episodes. About 100 languages, detected on their own, and translation to English.", "version": "0.1", "x-build-id": "VcE4lDEdjB2fzlayV" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/v0iddo~audio-transcription/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-v0iddo-audio-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/v0iddo~audio-transcription/runs": { "post": { "operationId": "runs-sync-v0iddo-audio-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/v0iddo~audio-transcription/run-sync": { "post": { "operationId": "run-sync-v0iddo-audio-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": { "mediaUrls": { "title": "Audio or video links", "type": "array", "description": "Direct links to media files: MP3, M4A, AAC, WAV, OGG, OPUS, FLAC, MP4, MOV, WEBM and more. Video files are transcribed from their sound track. Links to web pages (a YouTube or Spotify page) are not files and are refused.", "items": { "type": "string" } }, "podcastFeeds": { "title": "Podcast RSS feeds", "type": "array", "description": "RSS feed links of podcasts. The newest episodes of each feed are transcribed (see Episodes per feed). The feed link is on the show's website or its hosting page; Apple Podcasts and Spotify pages are not feeds.", "items": { "type": "string" } }, "episodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 200, "type": "integer", "description": "How many of each feed's newest episodes to transcribe.", "default": 1 }, "episodeKeywords": { "title": "Only episodes whose title holds", "type": "array", "description": "Keep only feed episodes whose title holds one of these words. Leave empty for the newest episodes.", "items": { "type": "string" } }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "es", "fr", "de", "pt", "it", "nl", "pl", "ru", "uk", "tr", "ar", "he", "fa", "hi", "bn", "ur", "id", "ms", "vi", "th", "tl", "ja", "ko", "zh", "sv", "no", "da", "fi", "cs", "sk", "hu", "ro", "bg", "el", "hr", "sr", "ca", "sw" ], "type": "string", "description": "The language spoken in the files. Detected from the first 30 seconds when left on Detect automatically; set it when the start is music or silence.", "default": "auto" }, "task": { "title": "Output language", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Write the text in the spoken language, or translate it to English.", "default": "transcribe" }, "model": { "title": "Model", "enum": [ "base", "small" ], "type": "string", "description": "Speech recognition model. Small is better with accents, noise and languages other than English, takes about twice as long and is charged as two minutes per minute.", "default": "base" }, "maxMinutesPerFile": { "title": "Maximum minutes per file", "minimum": 1, "maximum": 240, "type": "integer", "description": "Only the first this many minutes of each file are transcribed and charged; the row says when a file was cut.", "default": 120 }, "includeSegments": { "title": "Include timestamps", "type": "boolean", "description": "Return the transcript also as segments with start and end seconds.", "default": true }, "includeSubtitles": { "title": "Include SRT and VTT subtitles", "type": "boolean", "description": "Return the transcript also as SRT and WebVTT subtitle text.", "default": false }, "maxItems": { "title": "Maximum results", "minimum": 1, "maximum": 1000, "type": "integer", "description": "The run stops after this many result rows. It also caps what one run can cost.", "default": 100 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Leave as is: the run starts on the cheapest network the site accepts and switches to Apify Proxy automatically when the site blocks it. Pick proxy groups here only to force one specific network." } } }, "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 } } } } } } } } } }