{ "openapi": "3.0.1", "info": { "title": "Transcribe Audio & Video to Text: Speech to Text, SRT, VTT", "description": "Transcribe audio or video to text with open Whisper: direct media links, uploads or podcast RSS episodes. Use for speech-to-text or SRT/VTT subtitles. Input: mediaUrls or podcastRssUrls, optional model, language, outputFormats. Output per file: transcript, timestamped segments, SRT, VTT, minutes.", "version": "0.1", "x-build-id": "LKY7LcSM22etcnTlk" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/phaux~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-phaux-audio-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/phaux~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-phaux-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/phaux~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-phaux-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "mediaUrls": { "title": "Media file URLs", "type": "array", "description": "Direct links to audio or video files (mp3, m4a, wav, ogg, opus, flac, mp4, webm, mov, mkv ...), e.g. on your own server, S3/GCS signed links, Dropbox direct links or Apify storage. Web pages and platform links (YouTube, TikTok, Spotify, Apple Music, SoundCloud, Instagram, Facebook, X/Twitter) are refused.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "uploadedFiles": { "title": "Upload files", "type": "array", "description": "Upload your own audio/video files (stored in your Apify key-value store) or paste their links." }, "podcastRssUrls": { "title": "Podcast RSS feeds", "type": "array", "description": "Podcast RSS/Atom feed URLs. The newest episodes' audio enclosures are transcribed (see Max episodes per feed). The feed host's robots.txt is respected. Example: [\"https://feeds.npr.org/510289/podcast.xml\"].", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Max episodes per feed", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many of the newest episodes to transcribe from each feed (1–100). Default: 1.", "default": 1 }, "model": { "title": "Model", "enum": [ "base", "small", "tiny" ], "type": "string", "description": "Whisper model size. base = fast and good for clear speech (default). small = more accurate on accents, noise and names, about 3x slower. tiny = fastest, rough drafts. The price is the same for all models.", "default": "base" }, "language": { "title": "Language", "type": "string", "description": "Spoken language as a 2-letter code (en, de, es, fr, pt, it, nl, ja, zh ...), or auto to detect it. Setting it improves accuracy. Example: \"en\", \"de\" or \"\" for auto-detect. Default: \"auto\".", "default": "auto" }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 300, "type": "number", "description": "Only the first N minutes of each file are transcribed and charged (1–300). Caps the cost of long files. Default: 120.", "default": 120 }, "outputFormats": { "title": "Output formats (text, SRT subtitles, VTT captions)", "type": "array", "description": "text = full transcript; segments = timestamped segments; words = word-level timestamps; srt / vtt = subtitle and caption files for video players, YouTube Studio, Premiere, DaVinci Resolve or HTML5 (inline in each row and saved to the key-value store with srtUrl / vttUrl download links). Example: [\"text\", \"srt\", \"vtt\"]. Default: [\"text\", \"segments\", \"srt\", \"vtt\"].", "items": { "type": "string", "enum": [ "text", "segments", "words", "srt", "vtt" ], "enumTitles": [ "Plain text", "Timestamped segments", "Word timestamps", "SRT subtitles", "WebVTT subtitles" ] }, "default": [ "text", "segments", "srt", "vtt" ] }, "captionMaxCharsPerLine": { "title": "Caption max characters per line (SRT/VTT)", "minimum": 0, "maximum": 120, "type": "integer", "description": "Optional. 0 = off (default): one subtitle cue per transcript segment, exactly as before. Set e.g. 42 (broadcast/Netflix style) or 32 (phones, vertical video) to re-cut SRT/VTT cues at word boundaries so each line fits, using word timestamps. Only changes the srt/vtt output; price is the same.", "default": 0 }, "captionMaxLines": { "title": "Caption max lines per cue", "minimum": 1, "maximum": 3, "type": "integer", "description": "Lines per subtitle cue when 'Caption max characters per line' is set (1–3, default 2). Cues also never exceed 7 seconds.", "default": 2 }, "skipSilence": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Skip long silent parts with voice activity detection. Faster and avoids made-up text in silence. Billing is by audio length, not speech length. Default: true.", "default": true }, "maxFiles": { "title": "Max files", "minimum": 0, "maximum": 10000, "type": "integer", "description": "Stop after this many files (0 = all). Default: 0.", "default": 0 }, "timeBudgetSecs": { "title": "Time budget (seconds)", "minimum": 0, "maximum": 86400, "type": "integer", "description": "Stop after this many seconds and keep what is done; a file cut short is charged only for the minutes transcribed (0 = only the run timeout guard). Default: 0.", "default": 0 } } }, "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 } } } } } } } } } }