Audio and Video Transcriber: text, SRT and VTT subtitles
Pricing
from $9.00 / 1,000 audio minute transcribeds
Transcribes audio and video files you link to or upload, and podcast RSS episodes, into text with timestamps, SRT and VTT subtitles and the detected language. A Whisper speech model runs inside the actor; no outside service is called.
You can access the Audio and Video Transcriber: text, SRT and VTT subtitles programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "0.1", "x-build-id": "CMkICMpYHdxbg1hpD" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/examsens.ai~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-examsens.ai-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/examsens.ai~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-examsens.ai-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/examsens.ai~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-examsens.ai-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": { "fileUrls": { "title": "Audio or video file URLs", "type": "array", "description": "Direct links to audio or video files, up to 1 GB each: MP3, WAV, FLAC, Ogg, Opus, WebM or MKV, with Opus, Vorbis, FLAC, MP3 or PCM audio and AV1, VP8, VP9 or Theora video. Other files get an error item naming their format. Links to pages on video or social platforms such as YouTube or TikTok are refused. Use files you own or are allowed to process.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "uploadedFiles": { "title": "Upload audio or video files", "type": "array", "description": "Upload files from your computer. When the upload dialog asks for a store, choose a permanent or existing store, then pick that same store under \"Key-value stores with your files\" so the run can read it." }, "fileStores": { "title": "Key-value stores with your files", "type": "array", "description": "Apify key-value stores that hold your audio or video files. Every record whose key ends in .mp3, .wav, .flac, .ogg, .oga, .opus, .webm, .mkv, .mka or .ogv is transcribed. The run gets read access to these stores only." }, "podcastFeeds": { "title": "Podcast RSS feeds", "type": "array", "description": "Podcast RSS feed URLs. The newest episodes (see the next field) are taken from each feed's audio or video enclosures.", "items": { "type": "string" } }, "maxEpisodesPerFeed": { "title": "Episodes per feed", "minimum": 1, "maximum": 200, "type": "integer", "description": "How many of the newest episodes to transcribe from each podcast feed.", "default": 1 }, "model": { "title": "Speech model", "enum": [ "tiny", "base", "small" ], "type": "string", "description": "Whisper model size. tiny is the fastest, small is the most accurate, base sits between them.", "default": "base" }, "language": { "title": "Spoken language", "type": "string", "description": "Two letter language code of the speech, such as en, es, de, fr or ja. Leave empty to detect it from the first 30 seconds of speech.", "default": "" }, "translateToEnglish": { "title": "Translate the speech to English", "type": "boolean", "description": "Write the transcript and subtitles in English, whatever language is spoken.", "default": false }, "wordTimestamps": { "title": "Word timestamps", "type": "boolean", "description": "Add every word with its start time, end time and probability to each segment. Takes longer.", "default": false }, "vocabulary": { "title": "Names and terms to expect", "type": "string", "description": "Names, brands and jargon in the recording, separated by commas, so the model spells them right. The first 800 characters are used." }, "skipSilence": { "title": "Skip silence and music", "type": "boolean", "description": "Detect the parts with speech first and transcribe only those. Turn off if words go missing from quiet speech.", "default": true }, "maxMinutesPerFile": { "title": "Maximum minutes per file", "minimum": 1, "maximum": 600, "type": "integer", "description": "Transcribe at most this many minutes from the start of each file. Billing counts only the minutes transcribed.", "default": 120 } } }, "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 } } } } } } } } }}OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.
OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.
By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.
You can download the OpenAPI definitions for Audio and Video Transcriber: text, SRT and VTT subtitles from the options below:
If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.
You can also check out our other API clients: