MAI-Voice-2 is an earlier multilingual speech-synthesis model with voice prompting and expressive delivery controls. The standard release targets consistent long-form speech.
Official sources disagree: the June launch recommends 5–60 seconds, while the Foundry card specifies 10–120 seconds. Confirm the contract for the selected endpoint.
Model-specific retention and training-use policy not collected.
Caching
Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.
01 / INITIAL INPUTProcess & retain
The system processes eligible input and retains reusable state.
02 / LATER REQUESTCheck available state
Reuse depends on matching input, session state and the cache policy.
03 / CACHE HITReuse & generate
Reusing state can reduce repeated work. Any charges follow the billing rules below.
Azure Speech
Not verified
No endpoint-specific cache contract verified for this version.
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected
How to enable it
Not collected
Usage fields
Not collected
Billing rules
Not collected
Limits & data boundaries
Not collected
No verified cache rate for this endpoint. An empty rate is not a zero charge.
Caching reviewed 14 Oct 2026
What the measurements say
No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.
Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.
The record behind the model
Why it is included
Microsoft documents this as its internally developed MAI model, distributed through hosted Microsoft products or services. The reviewed materials provide no downloadable weights for this named model. Public Phi and MAI-DS-R1 families are not included by inference.
