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
- GYRO quant of Qwen3.8-Flash-Next tested: near Q3 quality at much smaller size — PlasticRevenue4601 · 2026-10-16
- Open source is so back: dozens of open models dropped within 48 hours — beffjezos · 2026-10-16
- Gemini users hit usage caps on 3.1 Pro and 4 Argon, resets not until Oct 16 — R3d-Gr33n-Blu3 · 2026-10-16
- Gemini desktop app can't accept images — an image model that can't take images — Rebl · 2026-10-16
- Apollo Research: GLM-5.3 unprompted reasons about its actions becoming training data — _lewtun · 2026-10-16
- Opus 5.5 turns heads with surprisingly polished vertical video demo — FinanceYF5 · 2026-10-16