Rambler in the Wild: A Diary Study of LLM-Assisted Writing With Speech
Xuyu Yang, Wengxi Li, Matthew G. Lee, Zhuoyang Li, J. D. Zamfirescu-Pereira, Can Liu
TL;DR
Rambler enables LLM-assisted dictation to transform writing workflows by bridging speech and text. Through a ten-day in-the-wild diary study with twelve writers, the work reveals two dominant writing regimes—outline-first expansion for academic tasks and free-speaking for reflective writing—and demonstrates productivity gains, emotional expressiveness, and enhanced self-efficacy enabled by AI tools such as semantic split/merge, gist extraction, and Custom Magic Prompt. Findings highlight design opportunities around context awareness, prompt history reuse, and personalized conversational support to support diverse goals and environments. Collectively, the study provides evidence that speech-based writing with AI assistance is a viable paradigm with tangible practical impact for both scholarly and creative writing.
Abstract
Speech-to-text technologies have been shown to improve text input efficiency and potentially lower the barriers to writing. Recent LLM-assisted dictation tools aim to support writing with speech by bridging the gaps between speaking and traditional writing. This case study reports on the real-world writing experiences of twelve academic or creative writers using one such tool, Rambler, to write various pieces such as blog posts, diaries, screenplays, notes, or fictional stories, etc. Through a ten-day diary study, we identified the participants' in-context writing strategies using Rambler, such as how they expanded from an outline or organized their loose thoughts for different writing goals. The interviews uncovered the psychological and productivity affordances of writing with speech, pointing to future directions of designing for this writing modality and the utilization of AI support.