LipCoder: Voice-Enabled Coding Toolkit
2026-08-31 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors created LipCoder, a programming tool that uses voice commands and sounds to help visually impaired people code more easily. Unlike typical tools that rely on screen readers, LipCoder provides better speech feedback and lets users navigate and edit code using natural language. They tested LipCoder with five visually impaired programmers, comparing it to common setups, finding useful ideas for making coding with speech more accessible. Their work aims to improve how blind or visually impaired coders interact with code using sound and voice.
AI-assisted programmingscreen readersspeech feedbackearcon cuesnatural language inputaccessibilityvoice-centric interfacesauditory designcoding environments
Authors
Hayoon Kim, Sungho Lee, Juhwi Kim, Bongwon Suh, Kyogu Lee
Abstract
AI-assisted programming environments have accelerated software development, giving rise to new paradigms like vibe coding. However, their benefits remain largely inaccessible to visually impaired programmers, as existing screen readers and assistive tools offer limited support for these emerging workflows. We introduce LipCoder, a voice-centric programming toolkit designed to deliver editor-level functionality through auditory and speech-based interfaces. LipCoder offers features comprising speech feedback and earcon cues for comprehension and validation, as well as natural language input for navigation and modification. In an exploratory evaluation, 5 visually impaired programmers performed a series of coding tasks comparing LipCoder with a baseline of VSCode, Copilot, and VoiceOver. Quantitative trends and qualitative feedback point to directions for auditory-first design that may broaden accessibility in speech-driven coding environments.