Multimodality

Chat can see and create text, images, videos, audio, music, and more.

For example, you can create an image simply by typing.

You could bring an image to life by turning it into a video.

Or, you could turn a video into words.

Chat can even turn a video into code.

Chat can remember context across conversations.

This means it can recall facts and context about your life, work, and environment.

With Memory, you'll get even more helpful responses and suggestions.

Chat can analyze data and offer actionable insights with Analysis.

And, it can perform precise calculations, allowing it to solve math problems with better accuracy.

Chat can access realtime knowledge from the internet.

And, it can access and read webpages.

Upload and chat with your PDF documents.

You can ask questions, get summaries, find information, and more.

Here's the tech specs.

And here's everything Chat can do.

Image-to-image, audio capabilities, some Memory capabilities, and Proactivity available later this year.