A Text-Native Interface for Generative Video Authoring (Video Preview)

A Text-Native Interface for Generative Video Authoring Bruce Liu, Mira Dontcheva, Ding Li UIST 2026 Video Preview for a UIST 2026 paper Everyone can write their stories in freeform text format -- it's something we all learn in school, yet authoring video requires one to learn specialized and complicated tools. In this paper, we introduce Doki, a text-native interface for generative video authoring. In Doki, writing text is the primary interaction: within a single document, users define assets, structure scenes, generate shots, refine edits, and add audio. We articulate the design principles of this text-native approach and demonstrate Doki's capabilities through examples. We ran a week-long diary study with 10 participants of varied expertise. Participants produced 46 videos, reporting faster idea‑to‑draft flow, improved coherence through parameterization, and clearer comprehension of narrative structure in the document view; they also surfaced limitations around model predictability, precise control, and temporal expressivity. With Doki, we explore a fundamental shift in generative video interfaces, and demonstrate a powerful and accessible new way to craft visual stories. Web:: https://programs.sigchi.org/uist/2026/program/content/262911