From the source

Run MiniMax Speech-02 models with an API

API release

Image published with the post by Replicate — Image from replicate.com

Replicate announces API availability for MiniMax Speech-02 text-to-speech models (HD and Turbo), with voice cloning, emotion control, and support for 30+ languages.

Pricing is $30 per million characters for Turbo, $50 per million for HD, and $3 per voice clone.

From the source
The Speech-02 series from MiniMax are text-to-speech models that let you create natural-sounding voices with emotional expression. The models have support for more than 30 languages.
replicate.com

Other stories

Replicate· 15 AprModel update

How to make remarkable videos with Seedance 2.0

Replicate· 24 FebCapability change

How to prompt Seedream 5.0

The Ultimate Guide to FLUX 3
Replicate· 4 AugNew model

Announced: 06 May 2025
Detected: 03 Aug 2026 21:12 UTC (+453d after)
Pricing: Turbo: $30 per million characters; HD: $50 per million characters; Voice cloning: $3 per voice

ModelsSpeech-02-HD, Speech-02-Turbo, Voice Cloning

Visit source ↗replicate.com