{ "openapi": "3.0.1", "info": { "title": "Video Transcriber - YouTube, TikTok, Instagram & X to Text", "description": "Transcribe any public video URL to text with timestamps: YouTube, TikTok, Instagram reels, X, Facebook, Vimeo, Loom, LinkedIn, podcasts, direct files. Platform captions first ($1.80 per 1,000 videos), built-in Whisper otherwise ($0.0054 per audio minute). SRT, VTT, translation. No login.", "version": "0.1", "x-build-id": "nYz1HTR6ARNl6XMgS" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/topapi~video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-topapi-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/topapi~video-transcriber/runs": { "post": { "operationId": "runs-sync-topapi-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/topapi~video-transcriber/run-sync": { "post": { "operationId": "run-sync-topapi-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", "properties": { "urls": { "title": "🔍 Video or audio URLs", "type": "array", "description": "One link per line: YouTube (videos, Shorts, channels, playlists), TikTok, Instagram reels/posts, X posts, Facebook videos/reels, Vimeo, Dailymotion, Loom, Wistia, LinkedIn posts, podcast feeds, Apple Podcasts shows, direct .mp3/.mp4/.m3u8 files, or any other page with a video.", "items": { "type": "string" } }, "urlsFromFile": { "title": "URLs from a file", "type": "string", "description": "Link to a public .txt or .csv file; every http(s) URL in it is transcribed (e.g. a Google Sheet exported as CSV)." }, "datasetId": { "title": "Dataset ID from another run", "type": "string", "description": "The dataset of a finished scraper run (TikTok, Instagram, YouTube, X...): the video URL in each row is found and transcribed, up to 10,000 rows." }, "datasetItems": { "title": "Rows from another scraper", "type": "array", "description": "Paste rows from any scraper's output instead of a dataset ID; a video URL is looked for in fields like url, videoUrl, webVideoUrl, postUrl." }, "transcriptSource": { "title": "🎯 Transcript source", "enum": [ "auto", "captions", "asr" ], "type": "string", "description": "Captions first reads the platform's own caption track when the video has one (billed per video) and runs speech recognition otherwise (billed per audio minute).", "default": "auto" }, "language": { "title": "Spoken language", "type": "string", "description": "\"auto\" detects it. Or a code / name (en, es, pt, de, ja, \"Spanish\") to force speech recognition and to prefer that caption track. Setting it helps on short clips.", "default": "auto" }, "preferredCaptionLanguages": { "title": "Preferred caption languages", "type": "array", "description": "Caption tracks to pick, in order, when a video lists several (e.g. en, es). Empty = the video's own spoken-language track.", "items": { "type": "string" } }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Return English text whatever is spoken: an English caption track or YouTube's own translation when there is one, Whisper's translation otherwise. The spoken language stays in spokenLanguage.", "default": false }, "model": { "title": "Speech-recognition model", "enum": [ "auto", "tiny", "base", "small" ], "type": "string", "description": "Whisper model for videos without captions. Auto: English audio goes to tiny.en (as accurate as base on English, twice as fast), other languages to base. Small is the most accurate on accents, noise and non-English speech, about 3x slower than base. Same price per minute.", "default": "auto" }, "minWords": { "title": "✂️ Minimum words", "minimum": 0, "maximum": 1000, "type": "integer", "description": "A transcript with fewer words is returned as a free row (NO_SPEECH) and never charged; music-only clips leave 0-2 stray words.", "default": 1 }, "publishedAfter": { "title": "Published after", "type": "string", "description": "Only videos / episodes published on or after this date (2026-10-01) or within a period (\"7 days\", \"24 hours\"). Videos whose date is unknown are kept." }, "maxMinutesPerVideo": { "title": "Max minutes per video", "minimum": 1, "maximum": 600, "type": "integer", "description": "Speech recognition stops after this many minutes of one video (the row says it was truncated); caption transcripts are never cut.", "default": 120 }, "monitorMode": { "title": "🔁 Only new videos", "type": "boolean", "description": "Skip every video an earlier run with the same monitor name already transcribed (skipped videos are not charged).", "default": false }, "monitorStoreName": { "title": "Monitor name", "type": "string", "description": "Runs with the same name share the list of transcribed videos (a named key-value store on your account). Letters, digits, dashes.", "default": "video-transcriber-monitor" }, "outputFormats": { "title": "📦 Extra output", "type": "array", "description": "Plain text is always returned. Add timed segments, word timings (speech recognition only), SubRip / WebVTT subtitles, a \"[0:03 - 0:07] text\" transcript, or RAG chunks.", "items": { "type": "string", "enum": [ "segments", "words", "srt", "vtt", "timestamped", "chunks" ], "enumTitles": [ "Timed segments", "Word timings", "SRT subtitles", "WebVTT subtitles", "Timestamped transcript", "RAG chunks" ] }, "default": [ "segments" ] }, "chunkSize": { "title": "Chunk size (characters)", "minimum": 200, "maximum": 20000, "type": "integer", "description": "Target size of one RAG chunk; chunks end on segment boundaries and keep their start and end time.", "default": 1000 }, "maxVideosPerSource": { "title": "Max videos per channel / feed", "minimum": 1, "maximum": 5000, "type": "integer", "description": "How many of the newest videos to take from each YouTube channel or playlist and each podcast feed.", "default": 10 }, "maxResults": { "title": "Max transcripts", "minimum": 0, "maximum": 100000, "type": "integer", "description": "Stop after this many transcripts (0 = no limit). Error rows do not count.", "default": 0 }, "maxTotalMinutes": { "title": "Max audio minutes per run", "minimum": 0, "maximum": 1000000, "type": "integer", "description": "Stop speech recognition once this many audio minutes were billed in the run (0 = no limit). Caption transcripts still run.", "default": 0 }, "includeFailedRows": { "title": "Include failed videos", "type": "boolean", "description": "Return a free row with errorCode and error for every video that could not be transcribed (private, removed, no speech...).", "default": true }, "maxConcurrency": { "title": "⚙️ Parallel videos", "minimum": 1, "maximum": 10, "type": "integer", "description": "Videos resolved and downloaded at the same time (speech recognition runs one at a time).", "default": 4 }, "proxyConfiguration": { "title": "Proxy configuration", "type": "object", "description": "Optional. Leave empty: the actor goes direct first and moves to Apify datacenter, then residential proxy only for a site that refuses it. Set your own to route every proxied request through it." } } }, "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 } } } } } } } } } }