In August 2025 MiniMax has released the Speech 2.5 series, featuring ultra-realistic voice effects, expanded language support, and improved stability.
Compared to Speech 02, the update adds 16 new languages and voices, along with enhanced accent optimization for voice cloning, offering 6-second quick cloning.
If you'd like to access this model, you can explore the following possibilities:
Other
Read documentation on how to use Minimax API for their text-to-speech models
