Skip to content
Mi

MAI-Voice-2-Flash

MAI-Voice-2-Flash is a low-latency text-to-speech model from Microsoft AI for voice agents, assistants, call centers, accessibility, narration, and other interactive applications. It generates expressive 24 kHz mono speech across 15...

Input
  • text
Output
  • speech

Providers

Available through 1 free provider. Use the model ID and API settings below to connect.

Connection Details

Model ID
microsoft/mai-voice-2-flash
Base URL
https://ai-gateway.vercel.sh
Protocol
vercel-ai-gateway
Model Type
speech

Rate Limits

Free with $5 monthly credits

* The provider match may differ from this model. Check its docs for details.

Benchmarks

Compare scores and explore results by category.

Category performance

Chart metric

Elo scale: 0–1,200. Higher is better.

Audiorealism

#2

1,126 Elo

49% win rate

Text To Speech

#3

1,126 Elo

43.4% win rate

Scores from Design Arena

Frequently asked questions

Free access, setup, and what to expect.