aiqbench analysis
Microsoft's release of MAI-Transcribe-2-Streaming marks a significant advancement in real-time speech-to-text capabilities, achieving the lowest word error rate among 38 models while maintaining ultra-low latency suitable for active voice agents. The model's ability to generate accurate partial transcripts within 100ms allows AI systems to begin reasoning or invoking tools mid-sentence, effectively bridging the gap between audio input and actionable output. This development reinforces the industry trend toward optimizing inference speed without sacrificing accuracy, which is critical for next-generation conversational interfaces.
Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-Time Speech-to-Text Model on Artificial Analysis
Microsoft AI has released MAI-Transcribe-2-Streaming, its first real-time speech-to-text model. It ranks #1 of 38 models on Artificial Analysis AA-WER Streaming. It scores 2.5% WER at 0.13s on final transcripts and 2.5% at 0.12s on first partials. It covers 60 languages with continuous language detection and costs $0.54 per hour during the introductory period. It is available now in public preview on Microsoft Foundry. The post Microsoft AI Releases MAI-Transcribe-2-Streaming: #1 Real-Time Speech-to-Text Model on Artificial Analysis appeared first on MarkTechPost.
Microsoft AI has released MAI-Transcribe-2-Streaming, its first streaming speech-to-text (STT) model. It launched on October 1, 2026, alongside 2 text-to-speech models, MAI-Voice-2.1 and MAI-Voice-2.1-Flash. Artificial Analysis ranks it #1 of 38 models for final and first partial transcript accuracy. The model targets voice agents, live captions and dictation, where latency decides the experience.…
Excerpt shown under the publisher's RSS terms · 53 words · full text and figures are on the publisher's site
Related coverage
Getting Started with OmniVoice-Studio
KDnuggets · Jul 23, 2026
Microsoft targets ultra-realistic voice agents with its first streaming transcription model
SiliconANGLE · Oct 2, 2026
Microsoft AI Introduces MAI-Transcribe-1.5: 2.4% WER on Artificial Analysis, Best-in-Class FLEURS Accuracy, and Up to 5x Faster Long-Audio Transcription
MarkTechPost · Jun 8, 2026
How to Fine-Tune Nemotron 3.5 ASR for Your Language, Domain, or Accent
Hugging Face · Jun 4, 2026