{ "openapi": "3.0.1", "info": { "title": "Speech-to-Text Transcription", "description": "Transcribe audio and video from YouTube, TikTok, podcasts, X, and 1,000+ other sites or any direct media URL into accurate, speaker-labeled text. Uses World's best speech to text AI models with automatic language detection, multilingual support, and smart formatting.", "version": "1.0", "x-build-id": "gGjhMN9poK9zxHl8x" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/hgservices~speech-to-text/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-hgservices-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/hgservices~speech-to-text/runs": { "post": { "operationId": "runs-sync-hgservices-speech-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/hgservices~speech-to-text/run-sync": { "post": { "operationId": "run-sync-hgservices-speech-to-text", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "videoUrl": { "title": "Video / Audio Platform URL", "type": "string", "description": "URL on YouTube, Vimeo, TikTok, SoundCloud, X/Twitter, an RSS podcast episode, or any of the 1000+ sites yt-dlp supports. Provide exactly one of videoUrl or mediaUrl." }, "mediaUrl": { "title": "Direct Media File URL", "type": "string", "description": "Direct public URL to an audio or video file (mp3, mp4, wav, m4a, flac, ogg, webm, mov, mkv). Useful for files hosted on S3, public Google Drive / Dropbox direct links, or any HTTP(S) URL. Provide exactly one of videoUrl or mediaUrl." }, "maxAudioMinutes": { "title": "Max Audio Minutes", "minimum": 1, "maximum": 600, "type": "integer", "description": "Maximum length (in minutes) of audio to transcribe. Inputs longer than this will fail before any cost is incurred. Default is 240 (4 hours), maximum is 600 (10 hours, Deepgram's per-request ceiling).", "default": 240 }, "model": { "title": "Deepgram Model", "enum": [ "nova-3", "nova-2", "whisper-large", "whisper-medium", "whisper-base" ], "type": "string", "description": "Deepgram speech recognition model to use", "default": "nova-3" }, "language": { "title": "Language", "type": "string", "description": "Spoken language is detected automatically by Deepgram, with an automatic retry on `whisper-large` if the first pass returns no text — so you normally do not need to set this. To maximize delivery the actor currently auto-detects regardless of this value and does not force a language: a wrong or overly-specific language code is the most common cause of an empty transcript (Deepgram then listens only for that language and silently returns nothing for any other). Leave empty.", "default": "" }, "diarize": { "title": "Speaker Diarization", "type": "boolean", "description": "Identify and label different speakers in the audio", "default": true }, "smartFormat": { "title": "Smart Formatting", "type": "boolean", "description": "Apply formatting to dates, times, numbers, and more", "default": true }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Optional Apify Proxy. Off by default — most public media URLs and platforms download fine and faster without a proxy, and a proxy adds latency and cost. Direct media URLs are always fetched directly first and only fall back to this proxy if the direct attempt fails. Enable this (e.g. with the RESIDENTIAL group) only if a source is geo-restricted or blocks server IPs. YouTube and TikTok are handled by dedicated downloader Actors and ignore this setting.", "default": { "useApifyProxy": false } } } }, "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 } } }, "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 } } } } } } } } } }