{ "openapi": "3.0.1", "info": { "title": "Speech to Text API - Audio, Video & Podcast Transcription", "description": "Transcribe audio, video and podcast episodes to text with Whisper AI, in 99 languages. Get clean text, timestamps and SRT/VTT subtitles, or translate to English. Pay per audio minute.", "version": "0.1", "x-build-id": "J2XtnnCaaEpOpJWyv" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/sndzcc~speech-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-sndzcc-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/sndzcc~speech-to-text/runs": { "post": { "operationId": "runs-sync-sndzcc-speech-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/sndzcc~speech-to-text/run-sync": { "post": { "operationId": "run-sync-sndzcc-speech-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "urls": { "title": "Audio, video or podcast links", "type": "array", "description": "One per line: direct links to audio or video files (MP3, M4A, WAV, FLAC, OGG, MP4, MOV, WebM...), podcast RSS feeds, Apple Podcasts show or episode links, Dropbox or Google Drive share links, or web pages with an audio player. YouTube, TikTok, Instagram and Spotify links are not supported.", "items": { "type": "string" } }, "quality": { "title": "Quality", "enum": [ "fast", "accurate" ], "type": "string", "description": "Fast (Whisper base) is great for clear speech, podcasts and English. Accurate (Whisper small) is better for other languages, accents, noise and jargon, and costs more per minute.", "default": "fast" }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "es", "fr", "de", "it", "pt", "nl", "ca", "pl", "ru", "uk", "tr", "ar", "he", "hi", "zh", "ja", "ko", "id", "vi", "th", "sv", "da", "no", "fi", "cs", "el", "ro", "hu" ], "type": "string", "description": "Leave on auto-detect, or pick the language to make it faster and more reliable on short clips.", "default": "auto" }, "translateToEnglish": { "title": "Translate to English", "type": "boolean", "description": "Output the transcript in English, whatever language is spoken.", "default": false }, "maxEpisodesPerFeed": { "title": "Episodes per podcast", "minimum": 1, "maximum": 500, "type": "integer", "description": "For podcast feeds and Apple Podcasts show links: how many of the newest episodes to transcribe.", "default": 1 }, "episodesSince": { "title": "Only episodes published since", "type": "string", "description": "Optional date (YYYY-MM-DD) for podcast feeds." }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Transcribe at most this many minutes of each file (from the start). Protects you from paying for very long files by mistake.", "default": 120 }, "vocabulary": { "title": "Names and terms (optional)", "type": "string", "description": "Names, brands or jargon that appear in the audio, comma separated, so Whisper spells them right. Example: Apify, Kubernetes, María Pérez." }, "saveSubtitleFiles": { "title": "Save SRT, VTT and TXT files", "type": "boolean", "description": "Also save each transcript as SRT and VTT subtitles and a TXT file, with download links in the results.", "default": true } } }, "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 } } } } } } } } } }