microsoft / vibevoice

Microsoft's VibeVoice text-to-speech model that can generate long-form speech from text with sample voices.

microsoft / phi-4-multimodal-instruct

Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models.

microsoft / omniparser-v2

OmniParser is a screen parsing tool to convert general GUI screen to structured elements.

microsoft / phi-3-medium-4k-instruct

A 14B parameter, lightweight, state-of-the-art open model trained with the Phi-3 datasets that includes both synthetic data and the filtered publicly available websites data with a focus on high-quality and reasoning dense pro

microsoft / phi-3-mini-128k-instruct

Phi-3-Mini-128K-Instruct is a 3.8 billion-parameter, lightweight, state-of-the-art open model trained using the Phi-3 datasets

microsoft / phi-3-mini-4k-instruct

Phi-3-Mini-4K-Instruct is a 3.8B parameters, lightweight, state-of-the-art open model trained with the Phi-3 datasets

microsoft / textdiffuser-2

Academic and Research-only: Unleashing the Power of Language Models for Text Rendering

microsoft / kid

microsoft / bringing-old-photos-back-to-life

Bringing Old Photos Back to Life