Microsoft's First Native Real-Time Bidirectional Voice Model MAI Realtime Surfaces
testingcatalog · x · 2026-08-02
According to an exclusive scoop, Microsoft is secretly testing its first native real-time bidirectional voice model, MAI Realtime, within its MAI Playground.
The model supports full-duplex conversation (listening and speaking simultaneously) and can seamlessly switch between 17 languages. It currently offers two voices, Victoria and Grant, which are noticeably more natural than Copilot’s existing voice mode. Additionally, the model supports tool calls like web search, features configurable turn-taking mechanisms, and handles interruptions cleanly with low latency.
More from Models
- User Mocks Fable Model: Like a Drunk Crank Physicist, Useless for Math Research — jasondeanlee · 2026-08-02
- Why Multimodal Input Matters for AGI: DeepSeek & Anthropic's Approach — dotey · 2026-08-02
- MiniMax H3 Model Expected to Launch Tomorrow — Xianbao_QIAN · 2026-08-02
- User Reports: Claude Opus Excels at Precise Tasks but Fails as a Daily Driver — EXM7777 · 2026-08-02
- DeepSeek's Tiny Model Size Yields 40x Opus Throughput, Enabling Low Prices — gaganghotra_ · 2026-08-02
- KRAFTON Releases A.X-K2 Speech Model Supporting Any-to-Any Modality — KRAFTON · 2026-08-02