Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.audixa.ai/llms.txt

Use this file to discover all available pages before exploring further.

Audixa is a powerful Text-to-Speech API that converts your text into natural, human-like speech. With support for multiple voices, languages, and customization options, Audixa makes it easy to add voice capabilities to your applications.

​
Key Features

Premium Voices

Access a library of high-quality, natural-sounding voices in multiple accents and styles.

Fast Generation

Generate speech quickly with our optimized async workflow and low-latency infrastructure.

Simple API

Integrate in minutes with our straightforward REST API and official SDKs.

​
How It Works

Audixa uses an asynchronous workflow for audio generation:
1

Submit Request

Send your text to the /tts endpoint with your chosen voice and settings. You’ll receive a generation_id immediately.
2

Poll Status

Check the /status endpoint with your generation_id to monitor progress.
3

Download Audio

Once complete, the status response includes an url to download your WAV file.

​
Get Started

Quickstart Guide

Generate your first audio in under 5 minutes.

Authentication

Learn how to authenticate your API requests.

Voice Library

Browse available voices and choose the right one for your use case.

API Reference

Explore the complete API documentation.

​
New to Audixa?

Every new account includes 10,000 free credits to try out the service. Sign up now to get started.