---
id: "microsoft/mai-voice-2.1"
also: ["microsoft/mai-voice-2.1-20261001", "vercel/microsoft/mai-voice-2.1"]
cheapest_list_usd_per_m: "22.0 in, 0.0 out, at azure on openrouter"
cheapest_effective_usd_per_m: "22.0 in, 0.0 out, at azure on vercel"
context: 0
max_output: 0
input: ["text"]
output: ["speech"]
released: "2026-10-01"
api: ["/api/v1/audio/speech"]
params: ["max_tokens", "stop", "temperature"]
endpoints: 2
gateways: "openrouter (1), vercel (1)"
no_training: 2
trains: 0
retains_prompts: 0
---
# Microsoft AI: MAI-Voice-2.1

MAI-Voice-2.1 is our highest-fidelity, most expressive text-to-speech model, delivering rich, natural speech across 23 languages. It extends the MAI-Voice family with broad multilingual coverage, gated instant voice cloning, and strong long-form generation capabilities. With its detailed prosody, nuanced expressiveness, and studio-grade audio quality, MAI-Voice-2.1 is ideal for experiences where maximum voice quality and fidelity are required - long-form narration, brand-defining audio etc.