Microsoft: MAI-Transcribe 2

microsoft/mai-transcribe-2

transcription

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.

from openai import OpenAI

client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")
tr = client.audio.transcriptions.create(
    model="microsoft/mai-transcribe-2",
    file=open("audio.mp3", "rb"),
)
print(tr.text)

Related models

Whisper Large v3 Turbo

Voxtral Mini Transcribe

Nemotron 3.5 ASR Streaming 0.6B

GPT-4o Transcribe

GPT-4o Mini Transcribe