{ "openapi": "3.0.1", "info": { "title": "Audio Transcription & Speech to Text - Video, Podcasts, SRT", "description": "Turns audio and video files (your own uploads, direct file links, public podcast feeds) into text and subtitles (SRT/VTT) in ~99 languages, on the open-source Whisper model, run inside the tool (no API key).", "version": "0.1", "x-build-id": "fNx05TtrQvQEo51bw" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/afterstar~audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-afterstar-audio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/afterstar~audio-transcriber/runs": { "post": { "operationId": "runs-sync-afterstar-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/afterstar~audio-transcriber/run-sync": { "post": { "operationId": "run-sync-afterstar-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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 files", "type": "array", "description": "Direct links to audio or video files (mp3, m4a, wav, ogg, flac, mp4, mov, webm), or upload your own files. YouTube, TikTok, Spotify, Apple Podcasts and SoundCloud are not supported.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "audioFile": { "title": "Or upload your own file", "type": "string", "description": "Upload one of your own audio or video files (it goes to a key-value store in your account), or paste a link." }, "podcastFeeds": { "title": "Public podcast RSS feeds", "type": "array", "description": "RSS feed URLs. The newest episodes are transcribed (see the limit below). With 'Only new episodes', a scheduled run transcribes only episodes it hasn't seen.", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 500, "type": "integer", "description": "How many episodes per feed and run, at most.", "default": 1 }, "maxMinutesPerFile": { "title": "Max minutes per file (optional)", "minimum": 1, "type": "integer", "description": "A cost guard: only the first N minutes of each file or episode are transcribed and charged. The row says so (statusCode 'trimmed_at_max_minutes'). Empty = the whole file." }, "outputMode": { "title": "Feeds: which episodes", "enum": [ "all", "new" ], "type": "string", "description": "For podcast feeds: transcribe the newest episodes, or only episodes not seen in earlier runs (use this with a schedule).", "default": "all" }, "model": { "title": "Model", "enum": [ "small", "base" ], "type": "string", "description": "Accurate uses Whisper small ($0.009 per audio minute). Fast uses Whisper base ($0.005 per minute), about 3 times faster with more word errors.", "default": "small" }, "language": { "title": "Language", "type": "string", "description": "'auto' to detect, or a code such as en, de, es, fi.", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe in the language spoken, or translate the speech to English text.", "default": "transcribe" }, "outputFormat": { "title": "Output", "enum": [ "all", "text", "segments", "srt", "vtt" ], "type": "string", "description": "What each result contains. SRT and VTT files are saved in the run's key-value store, with links in the row.", "default": "all" }, "wordTimestamps": { "title": "Word timestamps", "type": "boolean", "description": "Each timed segment also lists its words with start and end times and a confidence (0-1), for karaoke-style captions, search or editing. Same price; a run takes about 10 % longer. The segments are included whatever the Output choice.", "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 } } } } } } } } } }