Audio & Video Transcriber: Speech to Text & SRT Subtitles
Pricing
from $5.00 / 1,000 audio minutes
Transcribe audio and video files to text with Whisper: MP3, MP4, WAV, M4A, WebM, OGG and more. 99 languages with auto-detect, timestamps, SRT/VTT subtitles, word timings and translation to English. No API key. Pay per audio minute.
You can access the Audio & Video Transcriber: Speech to Text & SRT Subtitles programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.
{ "openapi": "3.0.1", "info": { "version": "1.0", "x-build-id": "9cPWdiYFxeWSOXbSQ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/manageable_gully~audio-video-transcriber/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-manageable_gully-audio-video-transcriber", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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/manageable_gully~audio-video-transcriber/runs": { "post": { "operationId": "runs-sync-manageable_gully-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/manageable_gully~audio-video-transcriber/run-sync": { "post": { "operationId": "run-sync-manageable_gully-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 / video file links", "type": "array", "description": "Direct links to audio or video files (MP3, MP4, WAV, M4A, AAC, FLAC, OGG, OPUS, WebM, MOV, MKV). Google Drive (shared as 'Anyone with the link') and Dropbox share links are converted automatically. Max 1 GB per file. Platform pages such as YouTube or TikTok are not supported.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "uploadedFile": { "title": "Or upload a file", "type": "string", "description": "Upload one audio or video file from your computer instead of (or in addition to) links." }, "quality": { "title": "Quality", "enum": [ "fast", "accurate" ], "type": "string", "description": "Fast is good for clear speech in English and major languages. Accurate is better for accents, noisy audio, names and non-English languages.", "default": "fast" }, "language": { "title": "Spoken language", "enum": [ "auto", "en", "he", "ar", "es", "fr", "de", "it", "pt", "ru", "uk", "pl", "nl", "tr", "hi", "ja", "ko", "zh", "id", "vi", "th", "fa", "ro", "cs", "sv", "el", "hu", "da", "fi", "no" ], "type": "string", "description": "Leave on auto-detect, or pick the language for better accuracy. Whisper supports 99 languages; use the API to pass any ISO 639-1 code.", "default": "auto" }, "task": { "title": "Task", "enum": [ "transcribe", "translate" ], "type": "string", "description": "Transcribe keeps the spoken language. Translate outputs English text from any language.", "default": "transcribe" }, "outputFormats": { "title": "Files to create", "type": "array", "description": "Saved to the run's key-value store; links are included in each result.", "items": { "type": "string", "enum": [ "srt", "vtt", "txt", "json" ], "enumTitles": [ "SRT subtitles", "WebVTT subtitles", "Plain text", "JSON segments" ] }, "default": [ "srt", "vtt", "txt" ] }, "wordTimestamps": { "title": "Word-level timestamps", "type": "boolean", "description": "Add start/end time and confidence for every word (for karaoke captions, editing, search).", "default": false }, "skipSilence": { "title": "Skip silence (VAD)", "type": "boolean", "description": "Detect speech first and skip long silences and music. Reduces hallucinated text. Billing is by file duration either way.", "default": true }, "includeSegments": { "title": "Include timestamped segments in results", "type": "boolean", "description": "Add start/end timestamps for each sentence-like segment to every result.", "default": true }, "vocabularyHint": { "title": "Vocabulary hint", "type": "string", "description": "Optional: names, brands or jargon that appear in the audio (e.g. 'Apify, Kubernetes, Dr. Cohen'). Helps spelling." }, "maxMinutesPerFile": { "title": "Max minutes per file", "minimum": 1, "maximum": 240, "type": "integer", "description": "Longer files are transcribed up to this limit (and billed only up to it).", "default": 180 } } }, "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 & Video Transcriber: Speech to Text & SRT 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: