TAAFT
Free mode
100% free
Freemium
Free Trial
Deals

Minimax Speech 2.0 HD

By MiniMax
Flagship Speech-02 configuration built for ultimate quality. Speech-02-HD pairs an autoregressive Transformer with a Flow-VAE decoder and a learnable speaker encoder, enabling intrinsic zero-shot cloning across many languages and ranking at the top of major human-rated TTS benchmarks for realism and timbre similarity.
New Audio Gen 4
Released: April 2, 2025

Overview

High-fidelity Speech-02 model using AR Transformer plus Flow-VAE, aimed at top-tier zero-shot TTS quality and benchmark-leading naturalness.

About MiniMax

MiniMax is a Chinese AI company (Shanghai) focused on developing multimodal foundation models across text, image, audio, video, and music.

Industry: Artificial Intelligence
Location: Shanghai, CN
Website: minimax.io
View Company Profile

Tools using Minimax Speech 2.0 HD

No tools found for this model yet.

Last updated: February 25, 2026
0 AIs selected
Clear selection
#
Name
Task