MiniMax Audio

MiniMax Audio creates lifelike speech in multiple languages, with a variety of sounds.

Introduction

MiniMax Audio creates lifelike speech in multiple languages with diverse voices.

What is MiniMax Audio?

MiniMax Audio is a platform that upgrades the Speech-02 model, allowing users to create lifelike speech in multiple languages, with a variety of voices and accents. It can read files and URLs, handle long text (up to 200,000 characters), and provide features such as voice cloning and isolation.

How to use MiniMax Audio?

Users can enter text, files or URLs, select a voice, and generate lifelike speech. The platform also offers voice cloning functionality by providing 10 seconds of audio input.