Microsoft Debuts MAI Realtime 1 Speech-to-Speech Model at One Cent per Minute

Original title: 微软首款语音对语音模型:MAI Realtime 1 登场,起价每分钟 0.01 美元
78AI Score

At Ignite 2026, Microsoft unveiled MAI Realtime 1, its first speech-to-speech model, positioned as enterprise-grade realtime voice AI that handles interruptions, quick acknowledgments and noisy multi-speaker environments. Base audio pricing is $0.01 per minute with separate token-based reasoning fees, and Microsoft claims it beats GPT Realtime 2.1 on quality, speed and price. The model is compatible with the OpenAI Realtime API, already trialed by Agoda, and slated for Dynamics 365 Contact Center and Dragon Copilot.

Full Report

IT之家 November 18 news: At the Ignite 2026 conference held yesterday (November 17), Microsoft announced its first speech-to-speech model, MAI Realtime 1, positioned as real-time voice AI for real enterprise scenarios. The model can handle natural conversation details such as interruptions, quick confirmations, and waiting for the other party to finish speaking, and can understand user requests in noisy environments or when multiple people are speaking at the same time.

Microsoft's first speech-to-speech model: MAI Realtime 1 debuts, starting at $0.01 per minute

In terms of pricing, Microsoft says the base speech-to-speech usage fee for the model is $0.01 per audio minute (IT之家 note: approximately 0.067 yuan RMB at current exchange rates); if inference is involved, it is billed separately at $1 per million input tokens (approximately 6.7 yuan RMB at current exchange rates) and $5 per million output tokens (approximately 33.4 yuan RMB at current exchange rates).

Microsoft says MAI Realtime 1 can not only respond to speech in real time, but also invoke a stronger reasoning engine when a task requires deeper thinking, and connect to enterprise systems and tools to complete complex operations such as bookings and customer service handling; to adapt to different customers and industries, developers can also adjust its tone, style, and behavior through prompts.

Microsoft says that in public benchmarks and internal product evaluations, MAI Realtime 1 outperforms GPT Realtime 2.1 in quality, speed, and price, and is on the "performance-price" frontier on the Big Bench Audio speech reasoning and Tau-Voice agent task completion benchmarks.

Microsoft's first speech-to-speech model: MAI Realtime 1 debuts, starting at $0.01 per minute

Microsoft's first speech-to-speech model: MAI Realtime 1 debuts, starting at $0.01 per minute

Test data released by Microsoft shows that MAI Realtime 1 achieves 98.9% accuracy on Big Bench Audio, with an input audio cost of about $1.35 per hour (approximately 9 yuan RMB at current exchange rates); by comparison, GPT-Realtime-2 High is 96.6% at $4.14 per hour (approximately 27.7 yuan RMB at current exchange rates), and Grok Voice 2.0 is 97.2% at $4.80 per hour (approximately 32.1 yuan RMB at current exchange rates).

The model is already compatible with the OpenAI Realtime API, making it easy for developers to test and migrate existing voice applications. Companies such as Agoda and Reservations.ai have begun trials.

Microsoft also plans to use it in Dynamics 365 Contact Center customer service scenarios, as well as in Dragon Copilot for AI-simulated patient conversations to help nurses practice clinical communication.