A Text-Native Interface for Generative Video Authoring

TL;DR

Doki introduces a text-native interface for generative video creation, enabling users to author videos through natural text writing, simplifying the process and making it more accessible.

Contribution

This paper presents Doki, a novel text-first interface for video authoring that aligns video creation with natural language writing, a significant shift from traditional tools.

Findings

Successful demonstration of Doki's capabilities through examples.

Positive user feedback in a deployment study with diverse participants.

Doki simplifies video creation, making it more accessible.

Abstract

Everyone can write their stories in freeform text format -- it's something we all learn in school. Yet storytelling via video requires one to learn specialized and complicated tools. In this paper, we introduce Doki, a text-native interface for generative video authoring, aligning video creation with the natural process of text writing. In Doki, writing text is the primary interaction: within a single document, users define assets, structure scenes, create shots, refine edits, and add audio. We articulate the design principles of this text-first approach and demonstrate Doki's capabilities through a series of examples. To evaluate its real-world use, we conducted a week-long deployment study with participants of varying expertise in video authoring. This work contributes a fundamental shift in generative video interfaces, demonstrating a powerful and accessible new way to craft visual stories.