Prompting the Muse: Generating Prosodically-Correct Latin Speech with Large Language Models

This paper presents a workflow that compels an audio-enabled large language model to recite Latin poetry with metrically accurate stress.One hundred hexameters from the Aeneid and the opening elegiac epistula of Ovid's Heroides constitute the test bed, drawn from the Pedecerto XML corpus, where ictic syllables are marked.A preprocessing pipeline syllabifies each line, converts alien graphemes into approximate English-Italian counterparts, merges obligatory elisions, adds commas on caesurae, upper-cases every ictic syllable, and places a grave accent on its vowel.Verses are then supplied, one at a time, to an LLM-based Text-to-Speech model under a compact system prompt that instructs slow, articulated delivery.From ten stochastic realisations per verse, a team of Latin experts retained the best; at least one fully correct file was found for 91% of the 200 lines.Upper-casing plus accent marking proved the strongest cue, while hyphenating syllables offered no benefit.Remaining errors cluster around cognates where the model inherits a Romance or English stress template.The corpus of validated audio is openly released on Zenodo, opening avenues for pedagogy, accessibility, and prosodic research.