#6969th of 93 in VoiceFor voice, speech and music
epub_to_audiobook
Converts EPUB books to per-chapter MP3 audiobooks using cloud or local TTS
- Stars
- 2.1k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
1,938 on 25 Apr 20262,084 on 14 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Command-line tool, with a Gradio web UI, that splits an EPUB into chapters and renders each as an MP3 through Azure TTS, OpenAI TTS, Edge TTS or a local Piper executable. Chapter titles are written as metadata for import into Audiobookshelf. It also has a preview mode that prints character counts, regex search-and-replace for pronunciation, parallel workers and chapter range selection.
Who it is for: Self-hosters turning EPUB ebooks into audiobooks for Audiobookshelf
Strengths
- Supports Azure, OpenAI, Edge (no key) and Piper local TTS from one CLI
- Preview mode prints per-chapter character counts before any paid TTS call
- Regex search-and-replace file fixes pronunciations and abbreviations
- Parallel chapters via --worker_count; titles embedded for Audiobookshelf
Weaknesses
- WebUI has no authentication and should not be exposed to the internet
- Azure and OpenAI voices need paid API keys; Piper needs a separate install
- Chapter title extraction can fail on EPUBs with unusual structure
- Kokoro works only via a local OpenAI-compatible endpoint with a dummy API key
What it needs
- no GPU
- Docker + Compose
- Needs Azure Speech key (Azure TTS), OpenAI API key (OpenAI TTS), Piper executable and voice models (Piper), Audiobookshelf (optional)
- Models: Azure TTS, OpenAI TTS, Edge TTS, Piper, Kokoro (via OpenAI-compatible endpoint)
- port 7860
What changed
From the release notes. No flag means the note does not say so, not that the upgrade is safe.
Also in Voice
See all 93| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 98 out of 100 |
| 2 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 92 out of 100 |
| 3 | whisper.cppC/C++ speech-to-text engine running OpenAI Whisper models locally | 90 out of 100 |
| #4 | meetilyDesktop app that records, transcribes and summarizes meetings locally | 87 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 84 out of 100 |