Fact · Dictation in your apps
The 2026 arXiv preprint Lost in Transcription names custom identifiers, such as variable and function names, as a central difficulty for speech input about code.
Checked against its source on October 17, 2026
In the source's own words
“custom identifiers such as variable and function names”
Lost in Transcription: How Speech-to-Text Errors Derail Code Understanding, Jayant Havare et al., arXiv, 2026, Abstract.
Open the original- What it measures
- The abstract says spoken queries about code face non-standard English, domain-specific vocabulary and custom identifiers. The study used four Indic languages and English.
- What it does not show
- Preprint. The study is about code understanding benchmarks, not about dictating prompts to a coding agent.
Source
Cited on
- Speech to Text for AI: Why Spoken Prompts Work BetterGuide
- Voice Input for Claude Code, Cursor and AI Coding ToolsGuide
- Do AI chatbots understand prompts with dictation errors?Question
- How do you dictate a good prompt for ChatGPT or Claude?Question
- Why does speech recognition get names and jargon wrong?Question