Abogen
Open-source app that turns e-books, PDFs and text files into audiobooks with synced subtitles, using Kokoro voices.
AI Audio & VoiceFreeverified Listed on Open source
Is Abogen free?
Yes, Abogen has a free plan. What you get: Open source (MIT license): free desktop and web app that runs offline on your computer. To get it: install espeak-ng; then install Abogen with WINDOWS_INSTALL.bat, uv or pip; then run abogen (desktop) or abogen-web (web UI) and convert a file. Verified on github.com.
Free plan at a glance
- Includes
- Open source (MIT license): free desktop and web app that runs offline on your computer
Free and open source under the MIT license, run on your own computer; the maker states no usage limit.
- Duration
- Free forever
- Commercial use
- Allowed on the free plan
How to get it free
Self-host- Install espeak-ng
- Install Abogen with WINDOWS_INSTALL.bat, uv or pip
- Run abogen (desktop) or abogen-web (web UI) and convert a file
Good to know
- On Windows, GPU acceleration works only with NVIDIA GPUs
- Word-level subtitles are English only
github.com, Checked Source
Overview
Abogen is a free, open-source (MIT) text-to-speech app that converts ePub, PDF, text, markdown and subtitle files into audio with matching subtitles. It uses the Kokoro model, runs on Windows, Mac and Linux, and can work fully offline once models are downloaded.
Key features
- Converts ePub, PDF, TXT, Markdown and SRT, ASS or VTT subtitle files
- Subtitles by line, sentence or word, in SRT or ASS formats
- Output as WAV, FLAC, MP3, OPUS or M4B audiobooks with chapters
- Voice mixer for custom voices, plus speed from 0.1x to 2.0x
- Queue mode for batch conversion with per-file settings
- Desktop app plus a web UI with Docker support and Audiobookshelf upload
Best for
- People
- Readers who want audiobooks of their own e-books, Creators making voiceovers with subtitles for YouTube, Instagram or TikTok, People who want text to speech that works offline
Limitations
- You install it yourself, with Python tools and espeak-ng
- Word-level subtitles work only for English text
- On Windows, GPU acceleration needs an NVIDIA GPU; AMD GPUs work only on Linux
Screenshot
FAQ
- Is Abogen free?
- Yes. Abogen has a free plan: Open source (MIT license): free desktop and web app that runs offline on your computer. We last checked github.com's pricing page on 2026-11-12.
- What does the Abogen free plan include?
- Open source (MIT license): free desktop and web app that runs offline on your computer. Source: https://github.com/denizsafak/abogen (checked 2026-11-12).
- How do I get Abogen for free?
- Steps: Install espeak-ng; Install Abogen with WINDOWS_INSTALL.bat, uv or pip; Run abogen (desktop) or abogen-web (web UI) and convert a file. Start at https://github.com/denizsafak/abogen (checked 2026-10-24).
- Do I need an account to use Abogen for free?
- Not for the free option: the free route is to self-host Abogen (Install espeak-ng). Checked 2026-10-24.
- What's the catch with Abogen's free plan?
- On Windows, GPU acceleration works only with NVIDIA GPUs. Word-level subtitles are English only. Checked 2026-10-24.
- What are free alternatives to Abogen?
- NaturalReader, Fish Audio and Kitten-TTS all have free plans. We checked their free offers on 2026-11-12.
- Can Abogen work offline?
- Yes. A menu option downloads all required models and voices so you can use Abogen completely offline without any internet connection.Source: github.com/denizsafak/abogen
- Which file types can Abogen convert?
- ePub, PDF, TXT, Markdown, and SRT, ASS or VTT subtitle files. It saves audio as WAV, FLAC, MP3, OPUS or M4B with chapters.Source: github.com/denizsafak/abogen
- Does Abogen need a GPU?
- No. Abogen still works on the CPU, but more slowly. On Windows only NVIDIA GPUs with CUDA are supported; AMD GPUs work on Linux with ROCm.Source: github.com/denizsafak/abogen
Free alternatives
NaturalReader
Text-to-speech reader for documents and web pages.
Free forever, Unlimited listening with free voices; 20,000 characters a day with Lite voices
Fish Audio
Text-to-speech and voice cloning.
Free forever, Limited monthly generations
Kitten-TTS
Open-source text-to-speech models with voice cloning that run in real time on a CPU, with no GPU needed.
Free forever, Run the models yourself; hosted API has 30 free minutes
TTSMaker
Free online text-to-speech tool with many voices.
Free forever, Free text-to-speech with weekly character limits
Luvvoice
Free unlimited AI text-to-speech.
Free forever, 10,000 characters a month, 3,000 per conversion
More free AI Audio & Voice tools
- MLX-Audio
Free forever, Open source (MIT license): free audio AI library you run on Apple Silicon Macs
- noScribe
Free forever, Free desktop app, transcription runs on your computer
- Speechnotes
Free forever, Unlimited dictation in the online notepad and Chrome extension, with ads
- Podcastfy
Free forever, Open source (Apache-2.0 license): free to run; local LLM and Edge TTS need no keys
- whisper.cpp
Free forever, Open source (MIT): free C/C++ speech recognition you build and run yourself
- Kokoro
Free forever, Open source (Apache-2.0 license): free model weights you run yourself with Python
Sources
- Free offer
- Verified on github.com/denizsafak/abogen
…project is available under the MIT License - see the LICENSE file for…
- Page content
Checked against
Added by our team. We check that a free option exists and record the date; signing up is between you and Abogen, so read their privacy policy and terms first.
Is this your tool? Claim it · Promote it
