About this project

aeneas is a powerful Python/C library and command-line tool designed for automatic forced alignment, which synchronizes text fragments with their corresponding audio narration. It generates synchronization maps that can be exported into a wide variety of formats, including subtitle files (SRT, VTT, TTML, SBV), digital publishing formats (SMIL for EPUB 3), and research formats (ELAN, TextGrid, Audacity). Key features include support for multiple text and audio formats, multilevel alignment (from paragraphs down to words), integrated TTS engines (such as eSpeak, AWS Polly, and Festival), and batch processing via job containers. It utilizes MFCC and DTW algorithms computed via C extensions for fast and robust alignment, making it a valuable tool for accessibility, digital publishing, and linguistic research.