v1.3.1

stanfordnlp/dspyv1.3.1Feb 6, 2026by denizsafak

AI Summary

This release introduces a major architectural expansion with a Flask-based Web UI and an EPUB 3 packaging pipeline, alongside advanced audio generation features like multi-voice support and GPU-accelerated TTS.

Key Highlights

Massive contribution (>55k lines) enabling Web UI and EPUB 3 pipeline.
New Flask-based Web UI (`abogen-web`) for Docker and headless deployments.
Supertonic TTS engine support with GPU acceleration.
Multi-voice 'theatrical' audiobook support with speaker/role assignment.
Integration with Calibre OPDS and Audiobookshelf.

New Features

EPUB 3 packaging pipeline
Flask-based Web UI
Supertonic TTS engine (GPU)
Entity analysis and pronunciation override
Speaker/role assignment for multi-voice
Calibre OPDS and Audiobookshelf integration

Full Release Notes

- Special thanks to [@jeremiahsb](https://github.com/jeremiahsb) for his [massive contribution](https://github.com/denizsafak/abogen/pull/120) (>55k lines!) that brought the Web UI, EPUB 3 pipeline, and core architectural improvements to life.
- Added an EPUB 3 packaging pipeline that builds media-overlay EPUBs from generated audio and chunk metadata.
- Persisted chunk timing metadata in job artifacts and exercised the exporter with automated tests.
- Added Flask-based Web UI (`abogen-web`) for Docker and headless server deployments.
- Reorganized codebase to support both PyQt6 desktop GUI and Web UI from a shared core.
- Added Supertonic TTS engine support with GPU acceleration.
- Added entity analysis and pronunciation override system for proper nouns.
- Added speaker/role assignment for multi-voice "theatrical" audiobooks.
- Added Calibre OPDS and Audiobookshelf integration.

Update:
```
uv tool update abogen
```