{ "openapi": "3.0.1", "info": { "title": "Universal Media Transcriber", "description": "Transcribe any video, audio or podcast link: YouTube, TikTok, Instagram, X, Spotify, podcast RSS, cloud files and 1,800+ sites. Get full transcripts, timestamps, speaker labels, SRT/VTT subtitles, summaries and RAG-ready chunks. 99 languages, no API key needed.", "version": "1.0", "x-build-id": "hfFfFmer6bGPF43mo" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/insights_data~universal-media-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-insights_data-universal-media-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/insights_data~universal-media-transcriber/runs": { "post": { "operationId": "runs-sync-insights_data-universal-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/insights_data~universal-media-transcriber/run-sync": { "post": { "operationId": "run-sync-insights_data-universal-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "๐Ÿ”— Media links", "type": "array", "description": "Links to transcribe, one per line: videos, Shorts, Reels, TikToks, X / Facebook / Instagram posts, podcast episodes, podcast RSS feeds, Apple Podcasts and Spotify shows or episodes, YouTube channels and playlists, SoundCloud tracks and sets, Google Drive / Dropbox / OneDrive share links and direct audio or video files (mp3, mp4, wav, m4a, ...). Feeds, shows, channels and playlists give their newest items.", "items": { "type": "string" } }, "searchQueries": { "title": "๐Ÿ”Ž Search queries", "type": "array", "description": "Search terms; each one adds the top results (as many as 'Items per feed / channel / search') from the platform chosen below.", "items": { "type": "string" } }, "searchPlatform": { "title": "๐Ÿ“บ Search on", "enum": [ "youtube", "soundcloud" ], "type": "string", "description": "Where the search queries run.", "default": "youtube" }, "audioFiles": { "title": "๐Ÿ“ค Upload audio or video files", "type": "array", "description": "Audio or video files from your computer (mp3, mp4, wav, m4a, mov, ...). Each file becomes one transcript." }, "inputFile": { "title": "๐Ÿ“„ File with links", "type": "string", "description": "A .txt (one link per line), .csv (any column with links) or .json file (rows of another scraper's output) with media links." }, "datasetId": { "title": "๐Ÿ“ฅ Dataset (chain another run)", "type": "string", "description": "Pick a dataset from another run (for example a TikTok, YouTube or podcast scraper), or give its ID through the API. One media link is taken from each row (up to 5,000 rows)." }, "transcriptStrategy": { "title": "๐Ÿชœ Transcript source", "enum": [ "auto", "captions", "whisper" ], "type": "string", "description": "Auto delivers the best available transcript for each item: a transcript the publisher already published, the platform's captions, or speech recognition when there is neither. 'Captions only' never runs speech recognition (items without captions come back as free no_captions rows). 'Always speech recognition' transcribes the audio itself.", "default": "auto" }, "acceptAutoCaptions": { "title": "๐Ÿช„ Accept auto-generated captions", "type": "boolean", "description": "Count the platform's auto-generated captions as captions. Turn off to use only creator-uploaded captions (other items go to speech recognition in Auto mode).", "default": true }, "usePublisherTranscripts": { "title": "๐Ÿ“ฐ Use the publisher's own transcript", "type": "boolean", "description": "When a podcast episode comes with a transcript published by its host, deliver that one (usually edited and with speaker names).", "default": true }, "language": { "title": "๐ŸŒ Spoken language", "type": "string", "description": "Language code of the recording (en, es, de, pt-BR, ...). Leave empty to detect it automatically. Also picks the caption track in that language when one exists." }, "model": { "title": "๐Ÿง  Speech model size", "enum": [ "auto", "tiny", "base", "small", "medium", "large-v3", "large-v3-turbo", "distil-large-v3" ], "type": "string", "description": "Size of the speech-recognition model. Auto picks a fast model that fits the run's memory. Bigger models are more accurate and slower. Memory needed: tiny and base 1 GB, small 2 GB, medium, distil-large-v3 and large-v3-turbo 4 GB, large-v3 8 GB; when the run has less, the biggest model that fits is used.", "default": "auto" }, "vocabulary": { "title": "๐Ÿ“– Vocabulary", "type": "string", "description": "Names, brands and jargon the recording contains, comma-separated, so speech recognition spells them right (for example: OpenAI, Anthropic, Claude, LangChain)." }, "wordTimestamps": { "title": "๐Ÿ”ค Word-level timestamps", "type": "boolean", "description": "Add start/end/confidence for every word inside each segment (karaoke captions, precise cuts). Uses speech recognition for every item.", "default": false }, "vadFilter": { "title": "๐Ÿ”‡ Skip silence and music", "type": "boolean", "description": "Skip silent and music-only parts: faster and no invented lines over silence.", "default": true }, "startAt": { "title": "โฉ Start at", "pattern": "^$|^\\d+(\\.\\d+)?\\s*(second|sec|minute|min|hour|hr|day|week|month|year)s?$|^\\d+(\\.\\d+)?\\s*(s|m|h)?$|^\\d+(:\\d{1,2}){1,2}(\\.\\d+)?$", "type": "string", "description": "Transcribe only from this point of the recording, counted from its start. Use a relative value; the picker lists days and weeks, so for minutes and hours type them in JSON input: 90 seconds, 10 minutes, 1 hour, 00:10:00 or 600. A calendar date cannot mark a point in a recording. Empty = from the start." }, "endAt": { "title": "๐Ÿ›‘ End at", "pattern": "^$|^\\d+(\\.\\d+)?\\s*(second|sec|minute|min|hour|hr|day|week|month|year)s?$|^\\d+(\\.\\d+)?\\s*(s|m|h)?$|^\\d+(:\\d{1,2}){1,2}(\\.\\d+)?$", "type": "string", "description": "Transcribe only up to this point of the recording, counted from its start. Use a relative value; the picker lists days and weeks, so for minutes and hours type them in JSON input: 20 minutes, 1 hour, 00:20:00 or 1200. A calendar date cannot mark a point in a recording. Empty = to the end (or the max minutes below)." }, "maxMinutesPerItem": { "title": "โŒ› Max minutes per item", "minimum": 1, "maximum": 600, "type": "integer", "description": "Longer recordings are transcribed up to this many minutes. Long recordings are processed piece by piece; more run memory gives more CPU and faster speech recognition.", "default": 120 }, "speakerLabels": { "title": "๐Ÿ‘ฅ Speaker labels", "type": "boolean", "description": "Mark segments, paragraphs and subtitles with Speaker 1, Speaker 2, ... (who speaks when). The audio is downloaded for this, also when captions exist, so runs take longer.", "default": false }, "numSpeakers": { "title": "๐Ÿ”ข Number of speakers", "minimum": 0, "maximum": 10, "type": "integer", "description": "How many people speak, when you know it (more accurate labels). 0 = detect automatically.", "default": 0 }, "speakerNames": { "title": "๐Ÿ“› Speaker names", "type": "array", "description": "Names for Speaker 1, Speaker 2, ... in order of who speaks first (for example: Host, Guest).", "items": { "type": "string" } }, "maxItemsPerSource": { "title": "๐Ÿ“Š Items per feed / channel / search", "minimum": 1, "maximum": 500, "type": "integer", "description": "Newest items taken from each podcast feed, Apple Podcasts / Spotify show, YouTube channel or playlist, SoundCloud artist or set, and search query (after the filters below).", "default": 2 }, "publishedAfter": { "title": "๐Ÿ“… Published after", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Only items published after this date. Pick a date (2026-09-01) or a relative window (30 days, 2 weeks, 6 months)." }, "publishedBefore": { "title": "๐Ÿ“† Published before", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Only items published before this date. Pick a date (2026-09-30) or a relative time (7 days = published more than 7 days ago)." }, "titleContains": { "title": "๐ŸŽฏ Title contains", "type": "string", "description": "Only items whose title contains one of these words, case-insensitive; separate alternatives with | (interview|Q&A)." }, "titleExcludes": { "title": "๐Ÿšซ Title excludes", "type": "string", "description": "Skip items whose title contains one of these words; separate alternatives with | (trailer|teaser)." }, "minDurationSeconds": { "title": "โณ Minimum duration", "minimum": 0, "type": "integer", "description": "Skip items shorter than this (when the source reports a duration). 0 = no minimum.", "default": 0 }, "maxDurationSeconds": { "title": "โŒš Maximum duration", "minimum": 0, "type": "integer", "description": "Skip items longer than this (when the source reports a duration). 0 = no maximum.", "default": 0 }, "includeShorts": { "title": "๐Ÿ“ฑ Include YouTube Shorts", "type": "boolean", "description": "For a YouTube channel link, also take the newest Shorts (in addition to the newest videos).", "default": false }, "searchTerms": { "title": "๐Ÿ”” Keywords to monitor", "type": "array", "description": "Brands, names or keywords to find in every transcript. Each hit is listed with its timestamp, the words around it and a link that opens the media at that moment.", "items": { "type": "string" } }, "cleanTranscript": { "title": "๐Ÿงน Clean transcript", "type": "boolean", "description": "Add cleanText: the transcript without um/uh, [Music] tags and stutters.", "default": true }, "ragChunkWords": { "title": "๐Ÿ“š RAG chunk size", "minimum": 0, "maximum": 5000, "type": "integer", "description": "Split each transcript into chunks of about this many words, with timestamps and links (ready for a vector database). 0 = no chunks.", "default": 300 }, "ragChunkOverlapWords": { "title": "๐Ÿงท Chunk overlap", "minimum": 0, "maximum": 1000, "type": "integer", "description": "Words repeated between neighbouring chunks so no idea is cut in half.", "default": 40 }, "subtitleMaxCharsPerLine": { "title": "๐Ÿ”  Subtitle characters per line", "minimum": 10, "maximum": 100, "type": "integer", "description": "Maximum characters per subtitle line (42 is the broadcast standard).", "default": 42 }, "subtitleMaxLines": { "title": "๐Ÿ“ Subtitle lines per cue", "minimum": 1, "maximum": 4, "type": "integer", "description": "Maximum lines shown at once.", "default": 2 }, "subtitleMaxSeconds": { "title": "๐Ÿ• Max seconds per subtitle", "minimum": 1, "maximum": 20, "type": "number", "description": "Longest time one subtitle stays on screen.", "default": 6 }, "includeSubtitlesInRecord": { "title": "๐Ÿ“ผ Include SRT / VTT in each row", "type": "boolean", "description": "Put the SRT and VTT subtitle text on every row. They are always in the Subtitles table too.", "default": true }, "includeSegments": { "title": "๐Ÿงฉ Include segments & paragraphs", "type": "boolean", "description": "Put the timestamped segments and readable paragraphs on every row (off = smaller rows). Segments are always in the Segments table too.", "default": true }, "includeFailedItems": { "title": "๐Ÿงพ Include failed items", "type": "boolean", "description": "Add a free row for every item that could not be transcribed, with the reason (no_speech, source_unavailable, bad_input, ...).", "default": true }, "exportFormats": { "title": "๐Ÿ’พ Export files", "type": "array", "description": "Also save each transcript as files in the run's key-value store; the row's files column links to them.", "items": { "type": "string", "enum": [ "srt", "vtt", "txt", "md", "docx", "json" ], "enumTitles": [ "SRT subtitles", "VTT subtitles", "Plain text", "Markdown", "Word (.docx)", "JSON" ] }, "default": [] }, "combinedReport": { "title": "๐Ÿ“‘ Combined report", "type": "boolean", "description": "One Markdown and one Word file with every transcript of the run, plus a run summary JSON, in the key-value store.", "default": false }, "watchlistId": { "title": "๐Ÿ‘€ Watchlist ID", "pattern": "^[\\w-]{0,64}$", "type": "string", "description": "Name for a memory of transcribed items that is kept between runs (letters, numbers, - and _). Use it with a schedule to follow a feed or channel." }, "newItemsOnly": { "title": "๐Ÿ†• Only new items", "type": "boolean", "description": "With a Watchlist ID: skip items transcribed by earlier runs, so a scheduled run delivers (and bills) only new uploads.", "default": false }, "cacheTranscripts": { "title": "๐Ÿ’ฝ Reuse saved transcripts", "type": "boolean", "description": "Keep each transcript and reuse it when the same item is run again with the same transcript settings, so re-running with new keywords, chunks or export files is fast.", "default": true }, "webhookUrl": { "title": "๐Ÿ“ฌ Webhook URL", "type": "string", "description": "Every finished row (without segments, subtitles and chunks) is also POSTed here as JSON (Zapier, Make, n8n, your server)." }, "maxRunMinutes": { "title": "โฐ Stop starting new items after", "minimum": 0, "type": "number", "description": "Items not started after this many minutes come back as free deadline rows. 0 = no limit.", "default": 0 }, "cookies": { "title": "๐Ÿช Cookies (cookies.txt)", "type": "string", "description": "Optional Netscape cookies.txt content for age-restricted or members-only media, or when YouTube asks to sign in. Stored encrypted." }, "maxConcurrency": { "title": "โšก Parallel downloads", "minimum": 1, "maximum": 16, "type": "integer", "description": "How many items are fetched at the same time. Speech recognition runs one item at a time.", "default": 3 }, "maxRetries": { "title": "๐Ÿ”„ Retries", "minimum": 0, "maximum": 10, "type": "integer", "description": "Retries for a failed request.", "default": 2 }, "autoUpdateYtDlp": { "title": "๐Ÿ†™ Refresh site support before the run", "type": "boolean", "description": "Update the built-in site support to its newest release before transcribing (adds about 10-20 seconds). Turn on if links from a site suddenly fail.", "default": false }, "proxyConfiguration": { "title": "๐ŸŒ Proxy", "type": "object", "description": "By default no proxy is used. If a site blocks the requests, the run switches to a datacenter proxy and then to a residential proxy (with up to 3 retries) and keeps it for the rest of the run. Pick a proxy here to start with it.", "default": { "useApifyProxy": 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 } } } } } } } } } }