Text-to-Video

A class of generative AI models that produces short video clips from natural-language prompts (and sometimes reference images). Examples at the time of writing include Runway Gen, OpenAI Sora, Google Veo, and Pika. For accessibility, text-to-video raises both opportunities — producing personalised reminiscence content, sign-language animation research, illustrative clips from plain-language descriptions, alternative media formats — and risks around factual accuracy, representation of disabled people, captioning, audio description, and epileptogenic motion. Accessibility reviews of T2V output should check for captions, reduced-motion alternatives, and faithful portrayal of users' intended scenes.