#77th of 38 in VoiceFor voice, speech and music
ebook2audiobook
Converts ebooks to chaptered audiobooks with local TTS and voice cloning
- Stars
- 20.4k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
18,300 on 31 Mar 202620,389 on 20 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Converts ebooks (epub, mobi, pdf, txt and about 20 other formats, with OCR for image pages) into audiobooks with chapters and metadata. It runs local TTS engines such as XTTSv2, Bark, Fairseq, VITS, Tacotron2, Tortoise, GlowTTS and YourTTS, with optional voice cloning. It offers a Gradio web UI and a headless CLI, and outputs m4b, mp3, flac, wav and other formats.
Who it is for: Self-hosters who want audiobooks from their own non-DRM ebooks
Ranked among open-source alternatives to ElevenLabs (#7 of 10) and Otter.ai (#8 of 10).
Strengths
- Supports 1158 languages via Fairseq/MMS models, plus optional voice cloning from a voice file
- Gradio GUI and headless CLI with batch directory mode and per-book voice map
- Runs on CPU, CUDA, ROCm, Apple MPS, Intel XPU and Jetson
- SML tags for pauses and voice switching; Audiobookshelf upload options in the CLI
Weaknesses
- README says modern TTS engines are very slow on CPU; lower-quality engines are advised
- EPUB has no standard chapter structure, so unwanted text must be removed manually
- Non-DRM ebooks only; DRM-protected files are not supported
- Docker on Windows requires virtualization enabled
What it needs
- RAM ≥ 2 GB
- GPU optional
- Docker + Compose
- Needs Docker (optional), Homebrew on macOS (auto-installed), Scoop on Windows (auto-installed)
- Models: XTTSv2, Bark, Fairseq, VITS, Tacotron2
- port 7860
Also in Voice
See all 38| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing and dictation with local speech models | 83 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 77 out of 100 |
| 3 | VoiceboxLocal voice studio for cloning, TTS, dictation and agent speech | 71 out of 100 |
| #4 | buzzOffline desktop app for transcribing and translating audio with Whisper | 69 out of 100 |
| #5 | meetilyDesktop app that records, transcribes and summarizes meetings locally | 68 out of 100 |