Microsoft AI: MAI-Transcribe 2

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 switch…

microsoft/mai-transcribe-2-20260903

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, speaker diarization, word-level timestamps, keyword biasing for domain-specific terminology, and configurable verbatim or clean transcription styles. It is suited for captions, call transcription, subtitling, accessibility, and other voice-enabled applications, and is faster than MAI-Transcribe-1.5 on long-form audio.

On OpenRouter, set `response_format` to `"verbose_json"` for segment timestamps, and add `timestamp_granularities: ["word"]` for word-level timestamps. Set `provider.options.azure.diarization.enabled` to `true` for speaker labels, provide keywords through `provider.options.azure.phraseList.phrases`, and select a transcription style through `provider.options.azure.enhancedMode.modelOptions.transcribeStyle`. See the [speech-to-text guide](https://openrouter.ai/docs/guides/overview/multimodal/stt).

Specifications & capabilities

Input
audio
Output
transcription
Context window · tokens
0
Capabilities
audioInput
Description source ↗

Published prices

1–1 / 1

microsoft/mai-transcribe-2 ↗

$0.10

Inference provider
openRouter
Platform
OpenRouter
Unit
hour
Currency
USD
Billing conditions
direction
input
Billing label
Input audio hour

Original sources

1–3 / 3

OpenRouter · Model page ↗

Epoch AI · Catalog ↗

OpenRouter · Catalog ↗

Source links

1–2 / 2

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace