{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcription – Speech to Text, SRT", "description": "Transcribe audio and video to text and SRT subtitles in 99 languages: English, Spanish, Portuguese, Chinese, Hindi, Arabic, French, German, Dutch. Translated subtitles, AI proofreading. No API key.", "version": "0.1", "x-build-id": "fce7gxu0nZ2gE0nNv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/olliolli~audio-video-transcription/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-olliolli-audio-video-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/olliolli~audio-video-transcription/runs": { "post": { "operationId": "runs-sync-olliolli-audio-video-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/olliolli~audio-video-transcription/run-sync": { "post": { "operationId": "run-sync-olliolli-audio-video-transcription", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "File links", "maxItems": 500, "type": "array", "description": "Direct links to your own audio or video files (mp3, m4a, wav, flac, ogg, opus, mp4, mov, webm, mkv). Share links from Google Drive, Dropbox and OneDrive/SharePoint are converted automatically (the file must be shared as \"Anyone with the link\"). Links to platform pages (YouTube, TikTok, Instagram, Spotify, Vimeo, ...) are not supported and cost nothing.", "items": { "type": "string" } }, "uploadedFiles": { "title": "Upload files", "type": "array", "description": "Upload audio or video files from your computer (they are stored in a key-value store of your Apify account)." }, "datasetId": { "title": "Links from a dataset", "type": "string", "description": "Take the file links from a dataset, e.g. the output of another actor. The actor only gets read access to the dataset you pick." }, "urlField": { "title": "Dataset field with the link", "type": "string", "description": "Name of the field that holds the file link in each dataset item. Use dots for nested fields (e.g. media.audioUrl).", "default": "url" }, "base64Files": { "title": "Base64 files (API)", "type": "array", "description": "For API use: a list of {\"name\": \"file.mp3\", \"data\": \"\"} objects. At most 25 MB per file." }, "language": { "title": "Language", "enum": [ "auto", "nl", "fr", "de", "en", "es", "it", "pt", "pl", "tr", "ru", "uk", "ar", "zh", "ja", "ko", "hi", "sv", "da", "no", "nn", "fi", "cs", "sk", "hu", "ro", "bg", "el", "hr", "sr", "sl", "bs", "mk", "sq", "lt", "lv", "et", "is", "fo", "ga", "cy", "br", "eu", "ca", "gl", "oc", "lb", "mt", "la", "he", "yi", "fa", "ur", "ps", "bn", "pa", "gu", "mr", "ta", "te", "kn", "ml", "si", "ne", "as", "sa", "sd", "th", "lo", "km", "my", "vi", "id", "ms", "jw", "su", "tl", "mg", "mi", "haw", "hy", "ka", "az", "kk", "uz", "tk", "tg", "mn", "ba", "tt", "be", "bo", "am", "sw", "so", "yo", "ha", "ln", "sn", "af", "ht", "yue" ], "type": "string", "description": "Language spoken in the files. \"Detect automatically\" works well for most files; setting the language helps for short files and accents.", "default": "auto" }, "outputFormats": { "title": "Output formats", "type": "array", "description": "Formats to include in each result. Plain text is always included.", "items": { "type": "string", "enum": [ "text", "segments", "srt", "vtt", "markdown" ], "enumTitles": [ "Plain text", "Segments with timestamps (JSON)", "SRT subtitles", "WebVTT subtitles", "Markdown" ] }, "default": [ "text", "segments", "srt", "vtt", "markdown" ] }, "translateTo": { "title": "Translated subtitles (optional)", "maxItems": 5, "type": "array", "description": "Also get the subtitles (SRT, VTT) and the text translated into up to 5 languages, with exactly the same timings as the original. The transcript itself always stays in the spoken language. Price: per started audio minute, per language (see Pricing); a language that fails or is already the spoken language is free. On the Apify free plan: 1 language per run.", "items": { "type": "string", "enum": [ "en", "es", "es-419", "pt-BR", "pt-PT", "fr", "de", "nl", "it", "zh-CN", "zh-TW", "ja", "ko", "hi", "ar", "id", "ru", "uk", "pl", "tr", "vi", "th", "ms", "tl", "bn", "ur", "fa", "he", "el", "ro", "cs", "hu", "sv", "da", "no", "fi" ], "enumTitles": [ "English", "Spanish (Spain)", "Spanish (Latin America)", "Portuguese (Brazil)", "Portuguese (Portugal)", "French", "German", "Dutch", "Italian", "Chinese (Simplified)", "Chinese (Traditional)", "Japanese", "Korean", "Hindi", "Arabic", "Indonesian", "Russian", "Ukrainian", "Polish", "Turkish", "Vietnamese", "Thai", "Malay", "Filipino", "Bengali", "Urdu", "Persian", "Hebrew", "Greek", "Romanian", "Czech", "Hungarian", "Swedish", "Danish", "Norwegian", "Finnish" ] }, "default": [] }, "vocabulary": { "title": "Names and terms (optional)", "maxLength": 5000, "type": "string", "description": "Names, brands and technical terms that occur in your recordings, separated by commas or new lines (e.g. \"Almere Binnen, Tenach, GNU Free Documentation License\"). Whisper gets them as a spelling hint, and the AI proofreading uses them too. Up to 600 characters are used. Free." }, "proofread": { "title": "AI proofreading (optional)", "type": "boolean", "description": "A language model corrects spelling, punctuation, capitalisation and clearly misheard words in the transcript, line by line, with the same timings. It does not rephrase or summarise; a suggested change that rewrites a line is not applied. The original text stays available in \"rawText\". Price per started audio minute (see Pricing); not charged if it fails.", "default": false }, "maxMinutesPerFile": { "title": "Maximum minutes per file", "minimum": 1, "maximum": 300, "type": "integer", "description": "Longer files are skipped (status skipped_too_long) and not charged.", "default": 120 }, "maxTotalMinutes": { "title": "Maximum minutes per run", "minimum": 1, "maximum": 600, "type": "integer", "description": "Files that would go over this total are not processed (status not_processed_limit) and not charged.", "default": 240 }, "maxFileSizeMb": { "title": "Maximum file size (MB)", "minimum": 1, "maximum": 2048, "type": "integer", "description": "Larger files are not downloaded (status too_large) and not charged.", "default": 512 } } }, "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 } } } } } } } } } }