Skip to main content
Audixa converts text into audio through an authenticated REST API. Choose a compatible voice and model, submit a generation, and poll its status until the audio is ready.

Key Features

Voice Catalog

List the voices available to your account and filter them by compatible model.

Asynchronous Generations

Submit work without holding a connection open, then track it with a generation ID.

Plain REST API

Integrate with standard HTTP tools such as native fetch, Python requests, or cURL.

How It Works

Audixa uses an asynchronous workflow for audio generation:
1

Submit Request

Send non-empty text to POST /v3/tts with voice_id, model, and audio_format. Each generation is billed for at least 30 characters (8 tokens). The response includes a generation_id and status.
2

Poll Status

Request GET /v3/tts?generation_id=... until the status is COMPLETED or FAILED.
3

Use the Audio

A completed response includes audio_url for the generated MP3 or WAV file.

Preview Before You Pay

Listen to the fixed samples at audixa.ai/voices to compare voices before purchasing. These samples use pre-generated text; they do not accept custom input and do not create a generation.
Audixa does not provide free generations or trial credits. Creating audio in the dashboard or API requires either a minimum $10 top-up or an active subscription.

Get Started

Quickstart Guide

Create and poll your first authenticated generation.

Authentication

Learn how to create and protect an API key.

Voice Library

List available voices and select one compatible with your model.

API Reference

Review endpoints, parameters, response fields, and errors.