Scenario
← All Models
Audio

Minimax Speech 2.6 (Turbo)

Use it ↗

Minimax Speech 2.6 (Turbo) provides low-latency text-to-speech in over 40 languages for real-time use, with fast generation starting from 9 CUs.

Released in October 2025, Minimax Speech 2.6 (Turbo) is a text-to-speech model optimized for speed. It prioritizes low-latency generation over the absolute highest audio fidelity, making it ideal for real-time applications like interactive voice chat and conversational AI. While sharing the same library of 300+ voices and 40+ languages as the HD version, its architecture is designed for minimal delay. This makes it suited for workflows where immediate feedback is critical, accepting a slight sacrifice in expressiveness.

More models from MiniMax