Text-to-Video (T2V) — Generative AI glossary — LiliDi
Generate a video clip from a text prompt only, with no reference image.
By LiliDi Editorial
Generate a video clip from a text prompt only, with no reference image. Text to Video (T2V) generates motion directly from a textual description — subject, action, camera, lighting. Sora 2, Veo 3.1 and Kling 3.0 lead on T2V quality in 2026. T2V is best when you do not have a reference frame and want maximum creative freedom; I2V is better for brand locked or character locked shots. Related: image to video, motion prompt.