Speech to Text - Audio Transcription

Convert audio files to text using AI-powered speech recognition. Supports multiple languages and engines.

Features

• Fast Processing: Lightning-fast speech to text - audio transcription powered by Azure
• Reliable: 99.9% uptime with automatic failover
• Scalable: Handle single requests or bulk operations
• Secure: Enterprise-grade security with API key authentication
• Well Documented: Comprehensive API documentation and examples

Use Cases

• Content Generation: Automate content creation workflows
• Data Analysis: Extract insights from unstructured data
• Automation: Integrate AI capabilities into your apps

Input Parameters

Parameter	Type	Required	Description
audioUrl	string	No	URL of the audio file to transcribe
audioBase64	string	No	Base64-encoded audio data (alternative to URL)
language	string	No	Language code (e.g., 'en', 'es', 'fr'). Leave empty for auto
includeSegments	boolean	No	Include time-stamped segments in the response
engine	string	No	Speech recognition engine to use
detectLanguageOnly	boolean	No	Only detect the language without full transcription

Output Format

{
  "success": true,
  "result": { ... },
  "timestamp": "2026-01-07T00:00:00Z"
}

Code Examples

JavaScript (Node.js)

import { ApifyClient } from 'apify-client';

const client = new ApifyClient({ token: 'YOUR_API_TOKEN' });

const input = {
  "audioUrl": "https://example.com/audio.mp3",
  "audioBase64": "example_audioBase64",
  "language": "en",
  "includeSegments": true,
  "engine": "azure",
  "detectLanguageOnly": false
};

const run = await client.actor("vivid_astronaut/speech-to-text").call(input);
const { items } = await client.dataset(run.defaultDatasetId).listItems();
console.log(items);

Python

from apify_client import ApifyClient

client = ApifyClient("YOUR_API_TOKEN")

run_input = {
  "audioUrl": "https://example.com/audio.mp3",
  "audioBase64": "example_audioBase64",
  "language": "en",
  "includeSegments": true,
  "engine": "azure",
  "detectLanguageOnly": false
}

run = client.actor("vivid_astronaut/speech-to-text").call(run_input=run_input)

for item in client.dataset(run["defaultDatasetId"]).iterate_items():
    print(item)

cURL

curl -X POST "https://api.apify.com/v2/acts/vivid_astronaut~speech-to-text/runs?token=YOUR_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
  "audioUrl": "https://example.com/audio.mp3",
  "audioBase64": "example_audioBase64",
  "language": "en",
  "includeSegments": true,
  "engine": "azure",
  "detectLanguageOnly": false
}'

Pricing

Model: Pay per result Price: $0.020 per result

You only pay for successful results. Platform usage costs are included.

API Documentation

Full API documentation is available at:

• Apify API Reference
• Actor API Endpoints

Support

• Issues: Report bugs via Apify Console
• Documentation: Apify Docs
• Community: Apify Discord

Version History

See ./CHANGELOG.md for version history.

---

Powered by Azure Cloud Infrastructure