Microsoft ships three voice models: MAI-Transcribe-2-Streaming and MAI-Voice-2.1 family
MicrosoftAI · x · 2026-10-02
Microsoft announced three new models: MAI-Transcribe-2-Streaming for accurate streaming transcription, plus MAI-Voice-2.1 and MAI-Voice-2.1-Flash, offering more natural speech and less waiting between turns — aimed at building voice agents that keep conversations moving.
More from Multimodal
- Video editor asks r/ how to keep characters consistent in ComfyUI microdramas — moonshoter · 2026-11-16
- Tencent's Hy4 Flash builds a 3D game with shield mechanics in 63 minutes, beating Hy4's 90 — ShunyuYao12 · 2026-11-16
- Hy4 Flash 3D voxel demo outpaces DeepSeek-V4.1 in same-prompt comparison — ShunyuYao12 · 2026-11-16
- Stunning AI-generated video: mechanical samurai armor in silver and blue — ZidanStudio · 2026-11-16
- AI-generated Red Rising fan video: Storytime with Papa Sevro — -VoiceoverAlex- · 2026-11-16
- Midjourney --sref trick: one style code yields fluffy rooster monsters, full params shared — michaelrabone · 2026-11-16