Audiorealism
#21,126 Elo
49% win rate
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...
Available through 1 free provider. Use the model ID and API settings below to connect.
* The provider match may differ from this model. Check its docs for details.
Compare scores and explore results by category.
Elo scale: 0–1,200. Higher is better.
1,126 Elo
49% win rate
1,126 Elo
43.4% win rate
Free access, setup, and what to expect.