Abogen

Abogen converts ePub, PDF, text, markdown, and subtitle files into audio with synchronized captions.

Abogen is a text-to-speech conversion tool designed to generate audio files and matching subtitles from various document formats. Users can input ePub, PDF, text, markdown, or subtitle files into the desktop application or web interface. The software processes the content using models like Kokoro-82M, allowing adjustments to speech speed, voice selection, and subtitle generation styles. It includes features such as a voice mixer for creating custom voices, batch processing queues, chapter controls for e-books, and options for saving output in formats like WAV, FLAC, MP3, OPUS, and M4B. The tool is intended for anyone needing natural-sounding speech and synchronized captions for projects like audiobooks or social media voiceovers.

Abogen at a glance

Best for: Writer, Social media creator
Runs on: Windows, macOS, Linux, Web, CLI, self-hosted, open source
Pricing: Free
Released: April 2025
Category: AI audio tool
Website: github.com/denizsafak/abogen

Key features

Convert ePub, PDF, text, markdown, and subtitle files to audio
Generate synchronized subtitles in various styles
Mix different voice models to create custom voices
Queue multiple files for batch processing
Select specific chapters or pages from documents
Adjust speech rate from 0.1x to 2.0x
Export audio in WAV, FLAC, MP3, OPUS, and M4B formats

Use it for

Generate audiobooks from ePub and PDF files
Create voiceovers for YouTube, Instagram, and TikTok
Produce audio with synchronized captions from text files

Alternatives to Abogen

ebook2audiobook — Convert multiple ebook formats into audiobooks with voice cloning and 1158 languages.
Audimind — It combines script editing, AI narration, smart alignment, and multi-track audio mixing in one workspace.
Fish Audio — Provides studio-grade voice cloning and text-to-speech with emotion control.
Applio — Runs locally with open-source code and no telemetry.
Folivox — It runs locally for free with CosyVoice 3 or integrates with online engines.
ElevenLabs — Natural AI voices, with 10,000+ voices in 70+ languages
AuK — It handles zero-shot TTS, editing, and enhancement via natural language.
VoxCPM — Provides tokenizer-free multilingual speech with controllable voice creativity.
NaturalReader — It offers content-aware AI voices in over 90 languages with cross-device compatibility.
Adobe Podcast — Enhances speech by removing background noise and echo with one click.
MOSS Transcribe — Jointly performs speech transcription and speaker diarization in one pass.
GPT-SoVITS — It allows high-fidelity voice cloning with as little as one minute of data.

All Abogen alternatives