Abogen
Local text-to-speech software turns books and documents into audio with synced captions, using Kokoro-82M in a desktop or self-hosted web interface.
Alternative to:
Abogen turns books, documents and subtitle files into narrated audio for readers making audiobooks and creators producing voiceovers. It can generate matching captions or follow timestamps for timed narration.
- Book conversion: Convert EPUB, PDF, Markdown and plain text into audio, with separate files for chapters or a merged audiobook.
- Captions and timing: Generate synchronized subtitles or use timestamps in text and subtitle files to control when each narration segment starts.
- Audiobook metadata: Add title, author and year details to M4B files, plus embedded cover images that Abogen can extract from EPUB or PDF files.
- Text preparation: The web interface offers optional LLM text normalization before speech generation.
- Audiobookshelf integration: Send finished audiobooks from the web interface to an Audiobookshelf library, automatically or for individual jobs.
Abogen is open source under the MIT license. It uses Kokoro-82M for speech generation and offers a desktop app alongside a self-hosted browser interface. The browser interface also supports Supertonic TTS; Supertonic, LLM normalization and Audiobookshelf integration are available only in that interface.
