microsoft

Microsoft AI: MAI-Transcribe 2

microsoft/mai-transcribe-2

Our take

AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.

OpenRouter's catalog describes microsoft/mai-transcribe-2 as a Microsoft AI multilingual speech-to-text model that accepts audio and returns transcription. It reports support for 60 languages, automatic language identification, and code switching for mixed-language speech. The supplied evidence is catalog-only and includes no independent model card or detailed evaluation data, so these capabilities should be treated as source-reported claims and validated on the intended audio workload.[1]

Strengths

Catalog-reported multilingual transcription across 60 languages.[1]
Catalog-reported automatic language identification for audio input.[1]
Catalog-reported code switching support for mixed-language speech.[1]

Limitations

Evidence is limited to OpenRouter's catalog; an independent model card was not available in this source pack.[1]
No detailed evaluation data, robustness evidence, or operating requirements were supplied; validate on representative workloads.[1]

Where to use it

Consider for pilots that need transcription of multilingual audio, subject to workload validation.[1]
Consider for mixed-language recordings where language identification and code switching are relevant.[1]

Sources

[1] OpenRouter catalog · Microsoft AI: MAI-Transcribe 2Sources checked: Nov 13, 2026

About this model

Description below is the original text supplied by OpenRouter, shown in the source language.

MAI-Transcribe 2 is a multilingual speech-to-text model from Microsoft AI, ranked #1 on the FLEURS multilingual benchmark. It supports 60 languages with automatic language identification, code switching for mixed-language speech,...

Specifications

Model ID: microsoft/mai-transcribe-2
Canonical ID: microsoft/mai-transcribe-2-20260903
Creator: microsoft
Added to OpenRouter: 03.09.2026
Context length: 0
Modality: audio->transcription
Input modalities: audio
Output modalities: transcription
Token pricing: No per-token price in the source snapshot — see OpenRouter for the billing unit
Knowledge cutoff: —
Expiration date: —

Tasks and capabilities

A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.

Task	Grade	Source-declared capability
General quality	No measurement	—
Coding	No measurement	—
Agents	No measurement	—
Writing	No measurement	—
Reasoning	No measurement	—
Document analysis	No measurement	—
Vision	No measurement	—
Image generation	No measurement	—
Audio	No measurement	input: audio
Video	No measurement	—
Embeddings	No measurement	—

Evaluations

No evaluations are supplied for this model.

How grades work

Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.

S — S — top 10% of the cohort
A — A — next 20% of the cohort
B — B — next 30% of the cohort
C — C — below the B band

Providers

Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.

Provider	Context length	Price in /1M	Price out /1M	Latency p50 (30m, s)	Throughput p50 (30m, tok/s)	Uptime (30m)
Azure	0	—	—	—	—	100%

Provider data retrieved: 13.11.2026

No published articles identify this model yet.