Why Text-to-Speech Fails at Explaining Code

Translating source code into speech creates a difficult dilemma between tedious character-by-character dictation and overly smooth summaries that omit crucial logic. This discussion explores the mechanics of code-to-speech translation, reviewing recent research on how major voice models misrepresent structural cues like indentation, pauses, and scope boundaries. It examines tools like speakable-text that use language-specific parsers to translate syntax into semantic narration, preserving operator precision, identifier conventions, and execution boundaries without reciting raw whitespace. Key sources: • Cardia, Angileri, Buzzi, Leporini, Code-to-Speech: An Exploratory Study of AI Text-to-Speech for Source Code Readability, ICMI '26, published 2026-10-04. — https://dl.acm.org/doi/full/10.1145/3776574.3831223 • `speakable-text`, MIT, v0.3.0 (2026-09-30), last push 2026-10-12. — https://github.com/atacan/speakable-text • `TextForSpeech`, frozen at v0.23.0; successor `SpeakSwiftly` v12.0.0. — https://github.com/gaelic-ghost/TextForSpeech Episode 6267 — myweirdprompts.com/n/6267 (permanent short link: myweirdprompts.com/262200)