Voice & audio

abogen

Turns ePub, PDF or text into narrated audio with matching subtitles

Visit official page 日本語で詳しく見る

Popularity

★ 5.8k

Last update

August 2026

License / pricing

MIT

What it does

Feed it an ePub, PDF, plain text, Markdown or subtitle file and it produces spoken audio plus subtitles synced to it - handy for audiobooks or for narration on short-form video. Speech comes from the Kokoro-82M model. On Windows there is a double-click installer script that pulls in everything it needs, though espeak-ng has to be installed separately first. MIT licensed.

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

Screenshots & visuals

Before you start

Setup difficultyEasy to start
Command lineRequired
API keyNot required
Sends data onlineYes

Judged automatically from the project's own metadata. Always confirm on the official page.

abogen FAQ

Is abogen free?: Yes. It runs on your own machine, so there is no usage-based cost either.
Do I need to install anything or write code to use abogen?: It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.
Does abogen work on a phone?: No. It needs a computer.
Can I use abogen commercially?: The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
abogen (this page)	Required	Not needed	Yes	No	Yes
kokoro-tts	Required	Not needed	No	No	Yes
MimikaStudio	Not needed	Not needed	No	No	No
Whisper	Required	Not needed	No	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.

Other voice & audio tools

kokoro-tts

Reads your EPUBs and PDFs aloud, chapter by chapter

MimikaStudio

Local voice cloning, read-aloud and audiobook studio for Apple Silicon Macs

Whisper

OpenAI's renowned speech-to-text model

Real-Time-Voice-Cloning

Clones a voice from a few seconds of audio (research implementation)

Browse all tools Home

What it does

Summary based on the project's own description. The Japanese page has a fuller beginner guide: setup difficulty, what to prepare, and a step-by-step start.

abogen FAQ

Is abogen free?

Yes. It runs on your own machine, so there is no usage-based cost either.

Do I need to install anything or write code to use abogen?

It needs the command line. If you are not comfortable typing commands, expect to get stuck during setup.

Does abogen work on a phone?

No. It needs a computer.

Can I use abogen commercially?

The licence is MIT, which permits commercial use. Conditions such as keeping the copyright notice still apply, so read the licence text before shipping it inside something.

How it compares

The conditions that decide whether you can actually use it, side by side.

Tool	Command line	API key	Sends data out	Phone	Commercial use
abogen (this page)	Required	Not needed	Yes	No	Yes
kokoro-tts	Required	Not needed	No	No	Yes
MimikaStudio	Not needed	Not needed	No	No	No
Whisper	Required	Not needed	No	No	Yes

"Sends data out" means your input is uploaded to someone's server. Pick "No" when the material cannot leave your organisation.