#5252nd of 67 in VoiceFor voice, speech and music
abogen
Converts ePub, PDF and text files to audiobooks with subtitles using Kokoro-82M
- Stars
- 6.2k
- License
- MIT
- Last commit
- Oct 2026
- Last release
- Feb 2026
- Language
- Python
4,172 on 3 Apr 20266,182 on 30 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Abogen turns ePub, PDF, text, markdown and subtitle files into speech with the Kokoro-82M model, and generates synced subtitles in SRT or ASS. It ships a PyQt6 desktop app (`abogen`) and a Flask web UI (`abogen-web`, port 8808) with a background job queue. Output formats include WAV, FLAC, MP3, OPUS and M4B with chapters.
Who it is for: People making audiobooks or voiceovers from documents locally
Strengths
- Outputs M4B with chapters, plus WAV, FLAC, MP3 and OPUS, with optional per-chapter files
- Subtitles by line, sentence or N words, in SRT or ASS
- Voice mixer blends Kokoro voices into saved profiles; batch queue with per-file settings
- Models can be pre-downloaded for fully offline use
Weaknesses
- Requires a separate espeak-ng install on every platform
- Web UI has features missing from the desktop app, such as Supertonic TTS and LLM normalization
- Setup is fiddly: CUDA-specific extras, pinned PyTorch, AMD GPU only on Linux
- Apple Silicon install needs Kokoro from git and numpy<2
What it needs
- GPU optional
- Compose
- Needs espeak-ng, PyTorch
- Models: Kokoro-82M, Supertonic TTS
- port 8808
Quick answers
Is abogen open source?
Yes. Its code is on GitHub under the MIT license.
Can you run abogen with Docker?
Yes. Its repository has a Docker setup: a Dockerfile, a Compose file or a published image.
Does abogen need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in Voice
See all 67| Rank | Project | Score |
|---|---|---|
| 1 | voicestudioDesktop app for voice cloning, dubbing, dictation and audiobooks | 97 out of 100 |
| 2 | whisper.cppC/C++ port of OpenAI Whisper for local speech-to-text transcription | 89 out of 100 |
| 3 | handyOffline push-to-talk dictation app that pastes transcripts into any text field | 89 out of 100 |
| #4 | xiaozhi-esp32ESP32 firmware for a voice chatbot with MCP device and cloud tool control | 82 out of 100 |
| #5 | buzzOffline desktop app for transcribing and translating audio with Whisper | 81 out of 100 |