Microsoft launches two AI models: MAI-Image-2.5-Pro and MAI-Voice-2-Flash.

Microsoft has officially launched two self-developed AI models, MAI-Image-2.5-Pro and MAI-Voice-2-Flash, and opened them for public preview. Both are built based on internal training processes. MAI-Image-2.5-Pro is Microsoft's most accurate image model to date, supporting main visual generation, detail editing, and in-image text rendering. MAI-Voice-2-Flash is optimized for high-concurrency voice scenarios and supports 15 languages.