Audiobook Factory
Turn ebooks into narrated audiobooks using a voice cloned from an audio recording, with optional character voices for dialogue.
- Python
- XTTS-v2
- WhisperX
- Voice cloning
Audiobook Factory combines voice preparation, ebook processing, speech synthesis, and audio assembly in a local workflow. Start with a voice recording and an EPUB, PDF, or plain-text book, then generate an audiobook with chapter markers.
The pipeline supports voice auditions, different voices for dialogue, resumable rendering, and optional transcription-based quality checks. A local dashboard brings together books, voice profiles, playback, and rendering progress.