Microsoft AI releases new MAI speech transcription and TTS models
Understand the story
Microsoft AI released the real-time speech transcription model MAI-Transcribe-2-Streaming and the voice model MAI-Voice-2.1. According to a report by The Decoder on October 2, 2026, MAI-Transcribe-2-Streaming ranks first in Artificial Analysis' accuracy rankings, supports 60 languages, and delivers first partial results with latency of just over 100 milliseconds. On pricing, Microsoft said the model will cost $0.54 per hour of audio through the end of 2026. A previous report established the theme of 'Microsoft AI releases new MAI speech transcription and TTS models'; this new report adds the specific model names, performance metrics, number of supported languages, latency figures, and pricing details. Public information is limited to the above reports, with no further developments disclosed.
AI overview of reporting · Updated 16 days ago
Reporting timeline
Explore different aspects of the story through its reporting.
- The DecoderMicrosoft AI releases new transcription and text-to-speech models for voice agents
Microsoft AI released MAI-Transcribe-2-Streaming, a real-time speech transcription model it says ranks first in accuracy on Artificial Analysis, supporting 60 languages, with first partial results delayed by just over 100 milliseconds and pricing of $0.54 per hour of audio before the end of the year, alongside the voice model MAI-Voice-2.1.