Text-to-video is a category of AI models that generate video sequences directly from a text prompt, including motion, scene composition, and, in some cases, audio. Examples of this category include Sora, Runway, and Google Veo, which enable rapid prototyping of video content without the need for a camera, actors, or expensive production.
Text-to-Video
The AI Act for Board Members: What Every C-Level Executive Needs to Know to Keep the Company from Paying Millions
6 min read
AI Governance in the Workplace: How to Set Rules for AI Use Before Regulators Do It for You
5 min read