MAI Voice 2
Microsoft voice with real style and speed controls.
The only engine on our roster with real style and speed controls.
Scores, speed, and the real rate.
The same trust rows as the open benchmark: a third-party quality score, our own measured latency, and the raw engine cost in the open.
- Quality Elo*
- 1007*
- Measured latency
- 2426ms measured 2026-06-10
- Languages
- 1 language
- Follows [cues]
- Plain read, ignores cues
- Engine cost
- $22/M in · $0 out rate checked 2026-06-11
The provider’s published rate when we last checked. Rates move, and when they do we update this row. It’s here so you can weigh our flat pricing against the raw cost underneath, instead of taking our word for it.
- Rights
- Commercial use; outputs are yours
* Quality Elo from the Artificial Analysis Speech Arena, retrieved June 10, 2026. It is a user-vote arena rating; the top model of all rated is Fun-Realtime-TTS at 1228.06. MAI Voice 2: Score is for MAI-Voice-1; MAI-Voice-2 is not yet arena-rated.
Latency is our own wall-clock time to full audio, measured 2026-06-10 on the same path that serves the studio. A measurement, not a server SLA.
Every voice MAI Voice 2 ships.
Press play to hear each voice: real output from this engine, recorded unedited. What you hear is what it produced.
Expressive American lead
One voice today. We list what is real rather than padding the roster.
Controls this engine genuinely accepts.
MAI Voice 2 is the rare engine that honors fine controls, so we render them. Every control below maps to a real parameter the engine accepts, not UI theater.
0.5x to 2x
Slows or hurries the read. Default 1x.
Expressive styles the engine performs. Neutral sends no style at all.
0.5 to 2
How hard the chosen style leans in. Only applies when a style is set.
Where MAI Voice 2 earns its place.
Styled English reads with speed and intensity control.
Hear it in the studio.
Open the studio and generate real audio through MAI Voice 2. No sign-up required to listen.