Search
Microsoft Unveils Advanced Image Editing & Generation and Ultra-Responsive Text-to-Speech Models
3 day ago /
Read about 0 minute
Author：小编
At the Build 2026 Developer Conference, Microsoft revealed an expansion of its proprietary AI model portfolio. The company introduced the high-fidelity image generation and editing model, MAI-Image-2.5, along with its Flash variant. These models empower users with sophisticated image editing capabilities and precise control over image fidelity. In tandem, Microsoft launched the public beta of its low-latency text-to-speech model, MAI-Voice-2-Flash. This model supports an impressive 15 languages and incorporates advanced voice cloning features, enhancing the user experience with its swift responsiveness.
-
C114 Communication Network -
Communication Home
7 X 24 Track global technological trends
