Quick Start

Get started with Suonora in minutes. Learn how to generate your first audio using our API.

API Reference

Explore our comprehensive API documentation, including endpoints, authentication, and examples.

Voice Gallery

Browse our collection of natural-sounding voices in multiple languages and styles.

Account Management

Learn about account balance and usage tracking.

​
What is Suonora?

Suonora is a powerful text-to-speech API that converts written text into natural-sounding speech. Our technology uses advanced AI models to generate high-quality, human-like voices in multiple languages.

​
Key Features

High-Quality Audio

Generate crystal-clear, natural-sounding speech with our advanced AI models.

Multiple Languages

Support for various languages and accents to meet your global needs.

Voice Customization

Adjust voice parameters like style, emotion, and speaking rate.

Real-Time Streaming

Stream audio in real-time for low-latency applications.

Easy Integration

Simple REST API with SDK support for Node.js.

Usage Tracking

Monitor your API usage and manage your account balance.

​
What’s in the Documentation?

Our documentation is organized into several sections to help you get the most out of Suonora:

​
Guides

  • Quick Start: Get up and running quickly with our step-by-step guide
  • Essentials: Learn about core features and best practices
    • Models: Overview of available AI models
    • API Responses: Understanding API responses and error handling
    • Balance: Managing your account and usage
    • Voices: Exploring available voices and their features

​
API Reference

  • Introduction: API overview, authentication, and base URL
  • Endpoints: Detailed documentation for each API endpoint
    • Speech API: Generate high-quality speech
    • Streaming API: Real-time audio streaming
    • Voices API: List and explore available voices
    • Balance API: Check account balance and usage

​
Getting Started

1

Create an Account

Sign up for a Suonora account at suonora.com to get your API key.

2

Choose Your Integration

Use our Node.js SDK or make direct API calls using your preferred programming language.

3

Generate Your First Audio

Follow our Quick Start Guide to create your first text-to-speech audio.

4

Explore Features

Try different voices, languages, and customization options to find what works best for your needs.

​
Need Help?

For the best experience, we recommend using our official Node.js SDK. It handles authentication, retries, and error handling automatically.

​
What this documentation covers

  • Base URL for all API requests
  • Authentication using your API key
  • Concurrency limits by subscription plan
  • Endpoints for voices, balance, and speech generation
  • Required parameters and usage examples
  • Response formats and common error codes

​
Base URL

https://api.suonora.com/v1

Use this as the base for all requests to the Suonora API.

​
Authentication

Every request must include your API key in the Authorization header:

Authorization: Bearer YOUR_API_KEY

You can generate and manage your API keys in the Suonora Dashboard.

​
Concurrency Limits

Each plan defines how many TTS jobs you can run at the same time. If your limit is reached, new requests are queued automatically.

PlanConcurrent Jobs
Personal ($5/mo)6
Superior ($10/mo)10
Pro ($29/mo)20

If the queue is full, you may receive:

  • 429 Too Many Requests
  • 503 Service Unavailable

Use exponential backoff when retrying.

​
Example Request

curl -X GET "https://api.suonora.com/v1/voices/list" \
     -H "Authorization: Bearer YOUR_API_KEY"

​
Example Response

response.json
{
  "success": true,
  "voices": [
    {
      "id": "axel",
      "name": "Axel",
      "gender": "Male",
      "locale": "de-DE",
      "mp3_preview": "https://storage.googleapis.com/suonora-public/voices/Axel.mp3"
    }
  ]
}