MAI-Voice-2.1-Flash Model Card

MAI-Voice-2.1-Flash is a prompted text-to-speech (TTS) model built in-house by the Microsoft AI team for fast, low-latency generation. It delivers high-fidelity, natural, and expressive speech across 23 languages while being optimized for real-time responsiveness, preserving human-like intonation, rhythm, and emotional nuance. Developers can control tone, emotion, and delivery through SSML, making it ideal for voice agents, call center agents, assistants, and other interactive scenarios where speed is critical. Voice can be configured using: • Curated voice library (licensed voices designed to work straight out of the box) • Voice Cloning via short audio clips (5-60 seconds), and the model matches the voice instantly