API Reference

Welcome to the Voice Cloning API service documentation. Our API provides powerful voice cloning capabilities that allow you to generate high-quality synthetic speech based on audio samples.

API Overview

Our API offers two main voice cloning approaches:

🚀 Synchronous Voice Cloning

• Use Case: Short text (less than 1000 characters)
• Response: Immediate results
• Processing Time: Completed within seconds
• Best For: Real-time applications, short phrase generation, quick testing

⏳ Asynchronous Voice Cloning

• Use Case: Long text (over 1000 characters)
• Response: Task queue processing
• Processing Time: 2-20 minutes depending on length
• Best For: Long-form content, batch processing, high-quality generation

Getting Started

1. Get API Key: Generate your API key in the user center
2. Prepare Audio Sample: Upload a 5-30 second clear audio file
3. Choose Endpoint: Select sync or async based on text length
4. Send Request: Call the API using your preferred programming language
5. Get Results: Download the generated voice file

Supported Audio Formats

• WAV: Recommended format, best quality
• MP3: Common format, good compatibility
• M4A: Apple device common format

Technical Specifications

Authentication

All API requests require your API key in the request header:

Authorization: Bearer YOUR_API_KEY

Pricing Information

⚠️ Important Notice: API interface services are only available for Professional and Unlimited version users.

Purchase Professional Version 

Error Handling

The API uses standard HTTP status codes and JSON-formatted error responses. All errors include a detail field providing detailed error descriptions.

Getting Help

If you encounter issues during usage:

1. Review the detailed API documentation
2. Check your API key permissions
3. Ensure audio samples meet requirements
4. Contact technical support for assistance