{ "openapi": "3.0.1", "info": { "title": "Audio & Video to Text - Speech to Text Transcription, SRT", "description": "Whisper transcription: audio to text and video to text from files, Drive/Dropbox links and podcast RSS feeds, with timestamps and SRT/VTT subtitles. 90+ languages, optional speaker labels. $0.006/min.", "version": "0.1", "x-build-id": "TnRaxI672XBp7vbES" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/tidytools~audio-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-tidytools-audio-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/tidytools~audio-transcriber/runs": { "post": { "operationId": "runs-sync-tidytools-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/tidytools~audio-transcriber/run-sync": { "post": { "operationId": "run-sync-tidytools-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": { "urls": { "title": "Audio or video file URLs", "type": "array", "description": "Main input (fill this, or `audioFiles` / `podcastFeeds` / `audioUrls` / `datasetId`). Links to audio or video files (MP3, WAV, M4A, AAC, OGG, OPUS, FLAC, MP4, MOV, MKV, WEBM...), up to 2 GB each, one per line. Public Google Drive, Dropbox and OneDrive share links work, and so does a web page with exactly one audio or video player. YouTube, TikTok, Instagram, Facebook, X, Vimeo, Loom, SoundCloud or Spotify page links are not files: they return a free error row explaining how to get the file.", "items": { "type": "string" } }, "audioFiles": { "title": "Or upload audio / video files", "type": "array", "description": "Upload recordings from your computer in Apify Console (they are stored in a key-value store of your account and read from there). Same formats and 2 GB limit as the URLs. In API calls, pass file URLs in \"urls\" instead." }, "podcastFeeds": { "title": "Podcast RSS feeds (optional)", "type": "array", "description": "Podcast RSS feed URLs or Apple Podcasts show links. The newest episodes are transcribed (see the next field). Each result includes the episode title and publish date.", "items": { "type": "string" } }, "audioUrls": { "title": "File URLs (request list, optional)", "type": "array", "description": "Same as \"Audio or video file URLs\", in Apify's request list format (also accepts a link to a text file with URLs). Kept for existing integrations; new integrations should use \"urls\".", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxEpisodesPerFeed": { "title": "Episodes per podcast feed", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many of the newest episodes to transcribe from each feed.", "default": 3 }, "usePublisherTranscripts": { "title": "Use publisher transcripts when the feed has them", "type": "boolean", "description": "Many podcasts publish their own transcript in the feed (Podcasting 2.0 : VTT, SRT, JSON, HTML or text). When an episode has one, it is downloaded and converted to the same output (text, segments, SRT/VTT for timed formats) with transcriptSource \"publisher\", and no audio minutes are charged. A transcript that is empty or does not match the episode length is ignored and the audio is transcribed as usual.", "default": true }, "episodesSince": { "title": "Episodes published since (optional)", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$|^(\\d+)\\s*(day|week|month|year)s?$", "type": "string", "description": "Only feed episodes published on or after this date (YYYY-MM-DD), or within e.g. \"30 days\". Applied before \"Episodes per podcast feed\". Filtered episodes get no row; SUMMARY.episodesFiltered counts them." }, "episodesUntil": { "title": "Episodes published until (optional)", "pattern": "^(\\d{4})-(0[1-9]|1[0-2])-(0[1-9]|[12]\\d|3[01])$", "type": "string", "description": "Only feed episodes published on or before this date (YYYY-MM-DD, the whole day counts)." }, "titleIncludes": { "title": "Episode title contains (optional)", "type": "array", "description": "Only feed episodes whose title contains one of these texts (case-insensitive). * matches anything, e.g. \"interview*ceo\".", "items": { "type": "string" } }, "titleExcludes": { "title": "Episode title does not contain (optional)", "type": "array", "description": "Skip feed episodes whose title contains one of these texts (case-insensitive), e.g. \"trailer\", \"rerun\", \"best of\".", "items": { "type": "string" } }, "language": { "title": "Language (optional)", "type": "string", "description": "ISO 639-1 code such as en, es, de, ja or zh. Leave empty to detect automatically." }, "vocabulary": { "title": "Vocabulary hints (optional)", "type": "string", "description": "Names, brands or terms that appear in the audio, e.g. \"Apify, Cloudflare, Kubernetes\". Helps spell them correctly." }, "saveSubtitles": { "title": "Save SRT and VTT subtitles", "type": "boolean", "description": "Also save subtitle files for every transcript (no extra charge).", "default": true }, "summarize": { "title": "AI summary and chapters", "type": "boolean", "description": "Add a short summary and timestamped chapters to each transcript. Charged as a separate event per file (see Pricing). Recordings shorter than 2 minutes get a summary only.", "default": false }, "speakerLabels": { "title": "Speaker labels (who said what)", "type": "boolean", "description": "Label each segment and paragraph with Speaker 1, Speaker 2… and count the speakers. Uses Deepgram nova-3 instead of Whisper and is billed as \"audio minute with speaker labels\" ($0.015/min) instead of the regular audio minute. Some languages (e.g. Chinese) are not available; those files fail with errorType \"unsupported\" and are not charged.", "default": false }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add a words array [{word, start, end}] to every segment (for video editing and precise subtitle alignment). Included in the regular $0.006/min price. With speaker labels on, the words come from nova-3 and the speaker-label price applies (not charged twice).", "default": false }, "subtitleLanguages": { "title": "Translated subtitles (optional)", "type": "array", "description": "Also make SRT + VTT subtitles in these languages (up to 5), e.g. Spanish, German, Traditional Chinese, ja. Timings and speaker labels are kept. $0.002 per audio minute per language, charged only for languages that succeed.", "items": { "type": "string" } }, "datasetId": { "title": "Read URLs from a dataset (optional)", "type": "string", "description": "A dataset from another Actor run, e.g. a podcast or video scraper. Its media URLs are added to the list above." }, "datasetField": { "title": "Dataset field with the URL (optional)", "type": "string", "description": "Field that holds the media URL, e.g. audioUrl or media.url. Leave empty to detect it (audioUrl, mediaUrl, videoUrl, url...)." }, "maxMinutesPerFile": { "title": "Max minutes per file (optional)", "minimum": 1, "type": "integer", "description": "Skip files longer than this. Skipped files get a result row with errorType \"too_large\" and are not charged. Empty = no limit." }, "maxTotalMinutes": { "title": "Max total minutes per run (optional)", "minimum": 1, "type": "integer", "description": "Stop charging for new files once this many audio minutes were transcribed. Files that would go over it get a row with errorType \"limit_reached\" and are not charged. Empty = no limit (your Apify spending limit still applies)." }, "maxConcurrency": { "title": "Parallel pieces per file", "minimum": 1, "maximum": 6, "type": "integer", "description": "Long files are split into 90-second pieces that are transcribed in parallel. More is faster.", "default": 3 }, "fileConcurrency": { "title": "Files in parallel", "minimum": 1, "maximum": 10, "type": "integer", "description": "How many files (podcast episodes, URLs) are downloaded and transcribed at the same time. More is faster for batches; rows then arrive in the order files finish (inputIndex gives the input position). Your max charge per run and maxTotalMinutes are still respected: the cost of every file in progress is reserved before it is transcribed. With little run memory fewer files run at once (about 3 at 1024 MB).", "default": 3 }, "fileTimeoutSecs": { "title": "Time limit per file (seconds)", "minimum": 0, "maximum": 7200, "type": "integer", "description": "A file whose download, conversion and transcription take longer than this is reported with errorType \"timeout\" and not charged; the run goes on with the next file. Raise it for recordings of several hours. 0 = no limit.", "default": 1800 }, "proxyConfiguration": { "title": "Proxy (optional)", "type": "object", "description": "Only used for requests sent from Apify's network (file downloads and podcast feeds). Apify proxy usage is billed to your Apify account." }, "newEpisodesOnly": { "title": "Only new episodes and files (for schedules)", "type": "boolean", "description": "Remember what was transcribed (podcast episode GUID or file URL) and skip it in later runs with the same monitor name. From podcast feeds, only episodes published after the newest one already transcribed are taken, so a run on a day without a new episode transcribes (and charges) nothing. Failed files are retried next time.", "default": false }, "backfillOlderEpisodes": { "title": "Also transcribe older episodes not done yet", "type": "boolean", "description": "With \"Only new episodes\": also take older episodes that were never transcribed (up to Max episodes per feed per run), to work through a back catalogue over several runs. Off by default, so scheduled runs only pick up new releases.", "default": false }, "monitorName": { "title": "Monitor name (for new episodes only)", "type": "string", "description": "Runs with the same name share the list of transcribed files, e.g. one name per podcast schedule. Letters, digits and dashes." } } }, "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 } } } } } } } } } }