MiniMax Speech 2.6 Turbo now available natively on Together AI

Together AI · 23 December 2025, 00:00

MiniMax Speech 2.6 Turbo, a multilingual text-to-speech model, is now available on Together AI's dedicated infrastructure alongside LLM and STT workloads. The model delivers sub-250ms latency, supports 40+ languages with real-time switching, includes 10-second voice cloning, and automatically adjusts emotional tone based on content context. This eliminates the need for developers to use multiple TTS providers and enables building production-grade voice agents on a single platform.

Why it matters

MiniMax Speech 2.6 Turbo: State-of-the-art multilingual TTS with human-level emotional awareness, sub-250ms latency, and 40+ languages—now on Together AI.