Models / MiniMax AI

Audio

MiniMax Speech 2.6 Turbo

Ultra-low latency TTS for production voice agents on Together AI.

This model is not available on Together’s Serverless API.

Model specifications

Model provider
MiniMax AI
Type
Audio
Main use cases
Text-to-Speech
Price
$30 / 1M characters + GPU hourly (by hardware)
Input modalities
Text
Output modalities
Audio

Category
Audio

Quickstart docs