MiniMax Speech 2.8

Text-to-speech with native sound tags: pauses, hesitations and fillers ("um", "ah"); voice cloning from a 10-second sample preserving texture and breathiness, background-noise and artifact removal, reduced accent artifacts across languages. Vendor announcement 2026-01-23.

Understands

text, audio

Produces

speech

Contents verified with the vendor: 2026-08-18

Included in subscriptions

No catalogue entry marks this model as part of a plan yet. It will appear here once the plan contents are confirmed with the vendor.