MAI Transcribe 2 Streaming is Microsoft's language model. A low-latency realtime speech-to-text model that streams audio over a WebSocket connection and returns live transcripts.
Specifications
Canonical IDmicrosoft-mai-transcribe-2-streaming
TypeLanguage
StatusActive
CreatorMicrosoftMicrosoft
Input ModalitiesText
Output ModalitiesText
Release Date · 12 days ago

Capabilities

Input1/5
Text✓
Image·
Audio·
Video·
PDF·
Output1/5
Text✓
Image·
Audio·
Video·
Embedding·
Capabilities0/13
Reasoning·
Adaptive Reasoning·
Function Calling·
Parallel Function Calling·
Structured Outputs·
Native JSON Schema·
Web Search·
URL Context·
Computer Use·
Code Execution·
File Search·
Prompt Caching·
Assistant Prefill·

Versions

VersionReleasedContextInput / 1MOutput / 1MStatus
MAI Transcribe 2 Streaming———Current
MAI Voice 2.1—$22.00—Available
MAI Voice 2.1 Flash—$15.00—Available
MAI Transcribe 2———Available
MAI Voice 2 Flash—$15.00—Available
MAI Voice 2—$22.00—Available
MAI Image 2 Efficient————Available
MAI Image 2.5—32K$5.00—Deprecated
MAI Image 2.5 Pro—32K$5.00—Deprecated
MAI Image 2.6—32K$5.00—Available
MAI Image 2.6 Flash—32K$1.75—Available

Model IDs

microsoft-mai-transcribe-2-streaming
microsoft/mai-transcribe-2-streaming