Microsoft: MAI-Transcribe-2-Streaming Compare

Microsoft: MAI-Transcribe-2-Streaming

MAI-Transcribe-2-Streaming is a speech to text model from Microsoft released on Oct 1, 2026. It reads audio and writes text.

Modalities
In / out price: n/a
Context: n/a
Max output: n/a
Released: Oct 1, 2026
Knowledge cutoff: n/a

Tool calling
Structured output
Reasoning
Prompt caching
Open weights
Free to use

More from Microsoft

MAI-Image-2.6
Image
Generates images from text.
by microsoftOct 13, 2026$5/M input tokens$38/M output tokens
MAI-Image-2.6-Flash
Image
Generates images from text.
by microsoftOct 13, 2026$1.75/M input tokens$19/M output tokens
MAI-Voice-2.1
Speech
Turns text into spoken audio.
by microsoftOct 1, 2026
MAI-Voice-2.1-Flash
Speech
Turns text into spoken audio.
by microsoftOct 1, 2026
MAI-Transcribe 2
Transcription
Turns speech into text.
by microsoftSep 3, 2026
MAI-Voice-2-Flash
Speech
Turns text into spoken audio.
by microsoftJul 23, 2026

All Microsoft models

MAI-Transcribe-2-Streaming questions

Is MAI-Transcribe-2-Streaming open source?

No. Microsoft serves it through an API only, so you cannot download the weights or host it yourself.

When was MAI-Transcribe-2-Streaming released?

Oct 1, 2026.

Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.