Microsoft launches new speech recognition model: MAI-Transcribe-2
Microsoft has unveiled MAI-Transcribe-2, a new speech recognition model supporting over 60 languages, featuring speaker identification and word-level timestamps.
What happened?
Microsoft has released the speech recognition model MAI-Transcribe-2. The model introduces new features including speaker diarization, configurable transcription styles, and word-level timestamps. According to Microsoft's internal benchmarks, the model achieves an average word error rate (WER) of 5.2 percent across 60 languages on the FLEURS benchmark.
Key facts
| Lanseringsdatum | 3 september 2026 |
|---|---|
| Felfrekvens (FLEURS) | 5,2 % i genomsnitt |
| Antal språk | 60 språk på FLEURS |
”With new features like diarization, configurable transcription styles, and word-level timestamps, MAI-Transcribe-2 beats other leading models like Gemini 3.5 Transcribe, GPT-Transcribe, Whisper V3-Large, and ScribeV2”
Why it matters
With MAI-Transcribe-2, Microsoft is challenging established speech models such as OpenAI Whisper V3-Large, Gemini 3.5 Transcribe, and GPT-Transcribe. According to measurements on the platform Artificial Analysis, the model ranks at the top regarding the balance between accuracy and latency.
Who is affected?
The model is aimed at developers and companies building applications for voice control, meeting transcription, and audio analysis. Existing users of previous transcription models will gain access to extended functionality and improved multilingual performance.
Impact on the EU
The model is delivered via Microsoft's cloud infrastructure and is covered by EU regulations on data protection and security, such as the GDPR. Speculation regarding additional specific requirements under the EU AI Act depends on the final application for speech recognition systems.
What else you should know
Microsoft’s claims that the model is the fastest, most accurate, and most cost-effective are based on the company's internal measurements as well as results from Artificial Analysis and the FLEURS benchmark. Exact pricing and full latency statistics are disclosed in conjunction with the launch on Microsoft’s AI portal.
Quick answers about this story
Vad har hänt?
När hände det?
Varför spelar det roll?
Vilka berörs av nyheten?
The link opens in a new window and leads to the publisher's own site.
Källan har spårats automatiskt från utgivaren via Aheadlines signalkedja.
AI-verktyg i artikeln
Topics
Get similar news straight to your inbox
The reader's room
Send in a question or an addition. The newsroom reads everything before it's published and replies when relevant. No AI-generated text – just people.
Sign in to submit a comment or question.
Read the article through your role
- Decide whether this affects strategy over 6–12 months or is just noise.
- Discuss with leadership: do we own the right question or does ownership need to move?
- Ask: what risk are we taking by NOT acting on this this quarter?
Generated angle — not editorial analysis of "Microsoft launches new speech recognition model: MAI-Transcr"