Realtime requires manual audio commits; server-side turn detection and noise reduction must be null. Session settings cannot change after the first audio append.Source for Input requirements (opens in a new tab)
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Speech recognition
Streaming audio transcription1
$0.54
audio hour
Rate conditions
Introductory USD rate for MAI-Transcribe-2-Streaming, per audio hour. No token conversion is applied. A future non-introductory rate was not collected. Transport-specific rounding, minimum charges and negotiated discounts were not verified.
Documented Speech SDK setModel selector; different from a Foundry Realtime deployment name.
Access
Azure Speech SDK with subscription key and resource region. Receive intermediate and final recognition events. PCM WAV file input is shown in SDK examples.
Prices retain their published currencies and billing units below.
Published billing units · original currency · observed 14 Oct 2026
Category
Usage
Rate
Unit
Speech recognition
Streaming audio transcription1
$0.54
audio hour
Rate conditions
Introductory USD rate for MAI-Transcribe-2-Streaming, per audio hour. No token conversion is applied. A future non-introductory rate was not collected. Transport-specific rounding, minimum charges and negotiated discounts were not verified.
Model-specific retention and training-use terms 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.
Microsoft Foundry Realtime
Not verified
No model-specific cache policy verified for this endpoint.
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
Azure Speech SDK
mai-transcribe-2-streaming
Not verified
No model-specific cache policy verified for this endpoint.
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 identifies this as its own MAI model, supplied through managed inference endpoints. The reviewed model documentation provides no downloadable model weights. This record does not classify public Phi or MAI-DS-R1 weights as closed.
