{ "openapi": "3.0.1", "info": { "title": "Audio & Video Transcriber – Whisper Speech to Text, SRT, VTT", "description": "Transcribe audio and video files and podcast RSS feeds to text with Whisper. Any direct mp3, m4a, wav, ogg, mp4 or webm link, Dropbox or Google Drive. 99 languages, auto-detect, translate to English, word timestamps. Get text, timestamped segments, SRT and VTT subtitles. From $0.009 per minute.", "version": "0.1", "x-build-id": "ebrvtZl55W7IYT87G" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/gazidev~media-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-gazidev-media-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/gazidev~media-transcriber/runs": { "post": { "operationId": "runs-sync-gazidev-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/gazidev~media-transcriber/run-sync": { "post": { "operationId": "run-sync-gazidev-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": { "mediaUrls": { "title": "Media file URLs", "type": "array", "description": "Direct links to audio or video files: mp3, m4a, wav, ogg, opus, flac, mp4, mov, webm, mkv and more. Podcast episode (enclosure) URLs, S3/CDN links, Dropbox and Google Drive share links (shared as 'Anyone with the link') and OneDrive links work. **YouTube, TikTok, Instagram, Spotify, Facebook, X, Vimeo and SoundCloud page links are rejected**: their terms of service forbid downloading. Only submit media you have the right to transcribe.", "default": [ "https://archive.org/download/spc141_1503_librivox/spc141_spiderandfly_lcw_64kb.mp3" ], "items": { "type": "string" } }, "podcastFeedUrls": { "title": "Podcast RSS feed URLs", "type": "array", "description": "Podcast RSS or Atom feeds. The newest `Max episodes per feed` episodes (audio/video enclosures) are transcribed.", "default": [], "items": { "type": "string" } }, "maxEpisodes": { "title": "Max episodes per feed", "minimum": 1, "maximum": 1000, "type": "integer", "description": "How many of the newest episodes to take from each feed.", "default": 3 }, "model": { "title": "Whisper model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "`base` (default): good accuracy for clear speech; a 60-minute podcast takes roughly 10–15 minutes. `tiny`: about 2× faster, for clean single-speaker English. `small`: most accurate (accents, noise, non-English), about 3× slower than base, billed with the `minute-transcribed-small` event.", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "`auto` detects the spoken language from the first 30 seconds. Or force a Whisper language code to skip detection and avoid mistakes on short or noisy clips: `en`, `es`, `de`, `fr`, `pt`, `it`, `nl`, `pl`, `tr`, `ru`, `uk`, `ar`, `hi`, `ja`, `ko`, `zh`, `id`, `vi`, `sv`… (99 languages).", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "`transcribe`: text in the spoken language. `translate`: Whisper translates the speech to English text and subtitles (same price).", "default": "transcribe" }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add a `words` list (start, end, word, probability) to every segment. Useful for karaoke-style captions, search and clip cutting. Adds about 10–20% processing time (same price).", "default": false }, "initialPrompt": { "title": "Vocabulary hint (initial prompt)", "type": "string", "description": "Optional text that helps Whisper spell names and jargon, e.g. `Apify, Crawlee, Kubernetes, Dr. Nguyen`." }, "vadFilter": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Voice activity detection skips silent parts. Faster and fewer hallucinated words in pauses and music. Timestamps still match the original file.", "default": true }, "maxDurationMinutes": { "title": "Max duration per file (minutes)", "minimum": 1, "maximum": 300, "type": "integer", "description": "Longer files are cut at this length (or skipped, see below). You are billed only for the minutes actually transcribed.", "default": 60 }, "longFileHandling": { "title": "Files longer than max duration", "enum": [ "truncate", "skip" ], "type": "string", "description": "`truncate`: transcribe the first N minutes (`truncated: true`). `skip`: do not transcribe the file at all (free error row).", "default": "truncate" }, "maxFileSizeMB": { "title": "Max file size (MB)", "minimum": 1, "maximum": 10000, "type": "integer", "description": "Downloads larger than this are stopped (free error row). Video files are big: 1 hour of 720p MP4 is about 500–1500 MB.", "default": 2000 }, "saveFiles": { "title": "Save .txt, .srt, .vtt and .json files", "type": "boolean", "description": "Store the transcript files in the run's key-value store and add download links (`txtFileUrl`, `srtFileUrl`, `vttFileUrl`, `jsonFileUrl`) to each row.", "default": true }, "includeSegments": { "title": "Include segments in dataset", "type": "boolean", "description": "Keep the timestamped `segments` array in each dataset row. Turn off for smaller rows (the JSON file still has them).", "default": true }, "downloadTimeoutSecs": { "title": "Download timeout (seconds)", "minimum": 30, "maximum": 3600, "type": "integer", "description": "Maximum time to download one file. Downloads are retried on network errors and HTTP 429/5xx.", "default": 900 } } }, "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 } } } } } } } } } }