# denizsafak/abogen

Generate audiobooks from EPUBs, PDFs and text with synchronized captions.

Repository: https://github.com/denizsafak/abogen
Canonical: https://ross.abutalabs.com/products/abogen
Homepage: https://pypi.org/project/abogen/
Language: Python
License: MIT
License Family: permissive
Topics: audiobook, audiobooks, content-creation, content-creator, epub-converter, kokoro, media-generation, narrator, speech-synthesis, subtitles, text-to-audio, text-to-speech, tts, voice-synthesis, kokoro-82m, kokoro-tts, ebook, epub, llm, voice-conversion
Last push: 2026-08-20T20:28:00+00:00

## Health v2 (maintenance only)
Score: 75/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 98, release rhythm 69, longevity 35
- inputs: {"age_days": 497, "days_push": 13, "days_rel": 208, "gap_med": 6, "n_releases_24m": 24}
- flags: none
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 5771, forks 429 (observed 2026-08-28T04:09:29.426063+00:00)

## What it is
Abogen is a desktop text-to-speech application that converts EPUB, PDF, text, markdown, and subtitle files into audiobooks with synchronized captions using the Kokoro-82M TTS model. It is a Python-based GUI tool available on Windows, Linux, and macOS.

## Use cases
- generate audiobooks from epub files
- convert pdf to audio with subtitles
- create voiceovers for youtube or tiktok videos
- turn text files into natural-sounding speech
- make synced caption videos from ebooks
- narrate documents with tts

## When to choose
- you want a ready-to-use GUI app for converting ebooks or documents to audio
- you need synchronized subtitles or captions alongside generated audio
- you want local, offline TTS using the Kokoro-82M model
- you create voiceover content for social media

## When to avoid
- you need a headless or API-driven TTS service for server integration
- you require the highest-quality neural voices beyond Kokoro-82M's capabilities
- you need real-time streaming speech synthesis
- you want a cloud-hosted solution with no local GPU/CPU setup

## Facets
- artifact type: application
- maturity: active
- function: tts, speech-recognition, audio-processing, pdf, gui
- domain: media, accessibility, developer-tools
- platform: windows, python
- tags: audiobook-generator, kokoro-tts, subtitles, epub-converter, voiceover, natural-language-processing, linux, macos, desktop

## Member repositories
- denizsafak/abogen (main) score 75

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:29.426063+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T17:52:54.588772+00:00, confidence not recorded.
  - readme: https://github.com/denizsafak/abogen (fetched 2026-08-28T04:09:29.426063+00:00, sha 846d834e33b9)
  - homepage: https://pypi.org/project/abogen/ (fetched 2026-08-29T08:48:14.733117+00:00, sha 4b4e8fead74a)
  - registry_pypi: https://pypi.org/pypi/abogen/json (fetched 2026-08-29T08:48:14.742340+00:00, sha 49a4d05858d5)
- Data as of 2026-08-30T08:39:29.467469+00:00.