The report says the transcription model supports 60 languages and begins returning partial transcripts just over 100 milliseconds after audio arrives. It lists MAI-Voice-2.1 for 23 languages and 26 locales, with Flash positioned for latency-sensitive workloads. Reported prices are $22 and $15 per million characters for the voice models, and an introductory $0.54 per audio hour for transcription through year-end. TestingCatalog says all three are available through Microsoft Foundry, MAI Playground, Vercel, and Azure Voice Live; the voice models are also available through OpenRouter. These are reported launch details and vendor claims, not independent performance verification.
Raw SignalOct 2, 20261 min read1 source
Microsoft launches MAI-Transcribe-2-Streaming Microsoft launched MAI-Transcribe-2-Streaming and two MAI-Voice models, offering real-time transcription, multilingual text-to-speech, low-latency audio generation, and voice cloning for conversational agents.
In one minute
Microsoft has launched MAI-Transcribe-2-Streaming alongside MAI-Voice-2.1 and MAI-Voice-2.1-Flash, according to TestingCatalog.