AI for Creators
Our work explores new pathways for AI to enhance the creative pursuits of artists and creators of all kinds, enabling rich experiences and revealing undiscovered avenues.
Empowering Creators with Enhanced AI
We're expanding global access to diverse content.
We prioritize developing real-time controllable systems that improve efficiency in editing, restoration, translation, and creation. Key areas of research include speech, language, music, sound, and visual technologies, with an emphasis on professional-grade precision and control.
Deep Dive into Our Research
Explore how our researchers are analyzing AI tools for creativity, with a focus on human artistic expression and the ability of technology to empower the creative spirit.
Music and Sound
Our current research is focused on where AI can impact various media. This includes the controllability and real-time functionality of AI foundation models with efficiency and speed for editing, restoration, creation, and the fine-grain control needed by professional creators in music, sound, 2D, and 3D.
Translation and Dubbing
Using speech analysis, synthesis, and large language models, we assist in labor-intensive tasks with high accuracy while seamlessly integrating cultural and linguistic nuances, enabling creators to connect with diverse audiences worldwide.
User Engagement Research
We aim to use the foundation model, along with LLMs and flexible natural language interfaces, to effortlessly provide insights for business users and content creators about their customers and content.
Industry Accolades & Awards
Recent Publications
See how our researchers are pushing the limits and contributing to the latest scientific findings in advanced AI technology for creators of all kinds.
Latest Updates from Sony AI
Explore our latest resources to stay informed on progress in advancing creative pursuits across visual realms, anime, dubbing, translation, music, sound, and beyond.
Blog
Inside the MMAudio Model: Unlocking the Future of Video-to-Audio Synthesis