Tts
The latest Tts coverage — news, analysis, and updates from the WindowsNews.AI desk.
Microsoft Launches MAI-1-Preview and MAI-Voice-1: First-Party AI Models Redefine Cost, Speed, and Audio
Microsoft has fired its opening salvo in the next phase of the AI arms race, but it isn't a declaration of war on its partners. Instead, the launch of the MAI model family—MAI-1-preview and...
Microsoft Bets on Specialized Agents with MAI-1 and Voice AI, Aiming to Slash Copilot Costs
Microsoft’s MAI initiative is no mere skunkworks project. In late summer 2025, the company began surfacing two homegrown models—a consumer-focused foundation language model and a high-speed...
Microsoft’s MAI-Voice-1 Powers Native Audio Generation in Copilot Labs — Here’s How to Try It
Microsoft has flipped the switch on native audio generation inside Copilot Labs, putting expressive, human-like voice synthesis into the hands of Windows users via its new MAI-Voice-1 model. The...
Microsoft Breaks OpenAI Grip with MAI Models: A New Era for Copilot and Cloud Margins
Microsoft has launched its first in‑house AI models, MAI‑Voice‑1 and MAI‑1‑preview, marking a strategic pivot that ends the company’s exclusive reliance on OpenAI for core artificial...
Microsoft Debuts In-House AI Models MAI-Voice-1 and MAI-1-Preview, Shifting Dependence from OpenAI
Microsoft has officially entered the in-house foundation model arena, unveiling MAI-Voice-1 and MAI-1-preview, two AI models built to power Copilot and Azure services while reducing the company’s...
Microsoft Rolls Out In-House MAI Voice and MoE Models to Slash Copilot Costs
Microsoft has taken the wraps off its first homegrown, production-grade AI models—MAI-Voice-1, a speech generator that can allegedly synthesize a full minute of audio in under one second on a...
Microsoft Ships In-House AI Models, Moving Copilot Beyond OpenAI Dependency
Microsoft has quietly deployed its first fully in-house AI models for consumer-facing Copilot experiences, a strategic pivot that reduces the company’s reliance on OpenAI’s technology and charts...
Microsoft VibeVoice Now Offers Real-Time TTS and Hour-Long ASR, But Original TTS Code Removed After Misuse
Microsoft’s VibeVoice project has grown far beyond its controversial debut as an hour‑scale multi‑speaker text‑to‑speech system. On August 25, 2025, the company released an open‑source...
On-Device AI Agent Lands in Windows 11 Settings, Powered by Mu Model on Copilot+ PCs
Microsoft has begun rolling out an AI agent directly inside the Windows 11 Settings app, a move that signals a concrete step toward the ambient, agentic operating system the company has been publicly...
Microsoft’s VibeVoice-1.5B TTS Model Generates 90-Minute Podcasts with 4 Speakers
Generating a 90-minute podcast episode with four distinct, expressive speakers without a recording studio or voice actors is no longer a far-off vision—it’s a research reality. Microsoft has...