{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber: Whisper Speech to Text, SRT", "description": "Transcribe audio and video files, podcast RSS feeds and Apple Podcasts links with Whisper. Dropbox, Drive and OneDrive links work. SRT, VTT and TXT files, word timestamps, 99 languages, translate to English. From $0.0085 per audio minute; failed files are free.", "version": "0.1", "x-build-id": "CpaRazapNJzFRyLs7" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/chris_elder~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-chris_elder-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/chris_elder~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-chris_elder-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/chris_elder~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-chris_elder-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", "required": [ "sources" ], "properties": { "sources": { "title": "Audio/video links or podcast feeds", "type": "array", "description": "One link per row. Supported: direct audio/video file links (MP3, M4A, WAV, OGG, OPUS, FLAC, MP4, MOV, WEBM, MKV and more), Dropbox, Google Drive and OneDrive share links, podcast RSS feeds and Apple Podcasts show or episode pages. YouTube, TikTok, Instagram, Facebook, X, Vimeo, Spotify and SoundCloud links are not supported.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "model": { "title": "Accuracy", "enum": [ "standard", "accurate" ], "type": "string", "description": "Standard is fast and good for clear speech. High accuracy handles accents, noise, names and non-English audio better and costs more per minute.", "default": "standard" }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "es", "fr", "de", "it", "pt", "nl", "pl", "ru", "uk", "tr", "ar", "hi", "id", "ms", "vi", "th", "ja", "ko", "zh", "sv", "da", "no", "fi", "cs", "ro", "hu", "el", "he", "fa", "ur", "bn", "ta", "tl", "sw" ], "type": "string", "description": "Leave on Auto-detect, or set the language to skip detection and improve accuracy. Whisper supports about 99 languages; the API also accepts any other ISO 639-1 code.", "default": "auto" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Output an English translation instead of the original-language transcript. Same price.", "default": false }, "subtitleFormats": { "title": "Files to save", "type": "array", "description": "Each transcript is also saved as these files in the run's key-value store, with download links in the dataset. Free.", "items": { "type": "string", "enum": [ "srt", "vtt", "txt", "json" ], "enumTitles": [ "SRT subtitles", "WebVTT subtitles", "Plain text (paragraphs)", "JSON segments" ] }, "default": [ "srt", "vtt", "txt" ] }, "includeSegments": { "title": "Include timestamped segments in the dataset", "type": "boolean", "description": "Adds a segments array (start, end, text) to each row. Turn off for a smaller dataset.", "default": true }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Adds the start and end time and confidence of every word. Useful for captions and editing tools. Slower, same price.", "default": false }, "vocabularyHint": { "title": "Vocabulary hint (names, jargon)", "type": "string", "description": "Optional. Names, brands or terms that appear in the audio, e.g. \"Apify, GPT Shop, Kubernetes\". Helps Whisper spell them correctly." }, "skipSilence": { "title": "Skip silence and music (VAD)", "type": "boolean", "description": "Voice activity detection skips long silences, which avoids made-up text in quiet parts. Billing still uses the file's audio length.", "default": true }, "maxEpisodesPerFeed": { "title": "Max episodes per podcast feed", "minimum": 1, "maximum": 1000, "type": "integer", "description": "For RSS feeds and Apple Podcasts show pages: how many of the newest episodes to transcribe.", "default": 3 }, "episodesSince": { "title": "Only episodes published since", "type": "string", "description": "Optional, for podcast feeds. Skips older episodes." }, "maxFiles": { "title": "Max files per run", "minimum": 1, "maximum": 5000, "type": "integer", "description": "Safety limit on the number of media files processed.", "default": 100 }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer files are transcribed up to this length and marked truncated. You are only charged for the minutes transcribed.", "default": 240 }, "maxFileSizeMb": { "title": "Max file size (MB)", "minimum": 1, "maximum": 4000, "type": "integer", "description": "Files larger than this are skipped (free).", "default": 2000 } } }, "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 } } } } } } } } } }