Reproduce “VoCa: Designing Speech-Canvas Interaction for Voice-Based Conversational Agents” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Yate Ge, Run Yuan, Yueran Qi, Wenjie He, Jiaqi Mo, Yangshuo Chen, Wenbin Zuo, Xiaohua Sun and 2 more

VoCa gives a voice agent a shared canvas to build on during open-ended conversations. Its planner coordinates speech with canvas actions, including notes, diagrams, and annotations that users can revisit. In a five-day deployment, 18 participants created 251 sessions; usability averaged 76.9 on the System Usability Scale, but the study did not compare VoCa with speech-only interaction.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.