{ "openapi": "3.0.1", "info": { "title": "Speech to Text: Audio & Video Transcription with SRT Subtitles", "description": "Transcribe audio and video files, podcast feeds and Google Drive or Dropbox links to text with NVIDIA Parakeet, one of the most accurate open speech models. Get sentence and word timestamps plus SRT and VTT subtitles. 25 European languages.", "version": "0.1", "x-build-id": "OGezzRpxuDcf4ZDQZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/jumblemog~speech-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-jumblemog-speech-to-text", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/jumblemog~speech-to-text/runs": { "post": { "operationId": "runs-sync-jumblemog-speech-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/jumblemog~speech-to-text/run-sync": { "post": { "operationId": "run-sync-jumblemog-speech-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Audio or video links", "type": "array", "description": "Direct links to audio or video files (MP3, M4A, WAV, FLAC, OGG, OPUS, MP4, MOV, MKV, WEBM and more), Google Drive or Dropbox share links, Apple Podcasts show links, or podcast pages that link to an RSS feed. Links to YouTube, TikTok, Instagram, Facebook, X, Vimeo, SoundCloud and Spotify aren't supported, because their terms don't allow downloading.", "items": { "type": "string" } }, "files": { "title": "Upload files", "type": "array", "description": "Upload audio or video files from your computer, or pick files you already stored in an Apify key-value store." }, "podcastFeeds": { "title": "Podcast RSS feeds", "type": "array", "description": "Podcast RSS or Atom feed URLs. The newest episodes are transcribed (see 'Episodes per feed').", "items": { "type": "string" } }, "episodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 100, "type": "integer", "description": "How many of the newest episodes to transcribe from each podcast feed or Apple Podcasts link.", "default": 1 }, "maxFiles": { "title": "Maximum files", "minimum": 1, "maximum": 1000, "type": "integer", "description": "Stop after transcribing this many files, so the cost of a run stays predictable.", "default": 100 }, "maxMinutesPerFile": { "title": "Maximum minutes per file", "minimum": 1, "maximum": 720, "type": "integer", "description": "Only the first this-many minutes of each file are transcribed and billed. Longer files are marked as truncated.", "default": 240 }, "outputFormats": { "title": "Files to save", "type": "array", "description": "Transcript files to save in the run's key-value store, with download links in each result: plain text, SRT subtitles, WebVTT subtitles and full JSON (segments and every word with timestamps).", "items": { "type": "string", "enum": [ "txt", "srt", "vtt", "json" ], "enumTitles": [ "Plain text (.txt)", "SRT subtitles (.srt)", "WebVTT subtitles (.vtt)", "Full JSON with word timings (.json)" ] }, "default": [ "txt", "srt", "vtt" ] }, "includeSegments": { "title": "Include sentence timestamps", "type": "boolean", "description": "Add the transcript split into sentences, each with a start and end time in seconds, to every result.", "default": true }, "includeWords": { "title": "Include word timestamps", "type": "boolean", "description": "Add every word with its start and end time to every result. Useful for clipping, highlighting and karaoke-style captions. Makes the dataset larger.", "default": false }, "maxCharsPerLine": { "title": "Subtitle line length", "minimum": 20, "maximum": 80, "type": "integer", "description": "Maximum characters per subtitle line in the SRT and VTT files (two lines per caption). 42 is the common broadcast standard; use about 32 for vertical videos.", "default": 42 } } }, "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 } } } } } } } } } }