About & Disclaimer

About this project

Book to Audiobook is an independent "ebook to audiobook" tool: import an EPUB / TXT ebook, parse chapters locally in your browser, and call a speech synthesis service to generate chapter audio. It supports a local library, online reading, listening progress, and MP3 / M4B export. Books, reading progress, and generated audio are stored locally in your browser (IndexedDB).

Technical origins

Part of this project's speech synthesis capability is based on the open-source project wangwangit/tts (VoiceCraft) and uses Microsoft Edge TTS technology. That project is released under the MIT License; this project retains its license information (see the LICENSE file). We thank the original author and the open-source community.

This project and VoiceCraft are two different products: VoiceCraft is an AI speech processing platform, while this project focuses on converting ebooks into audiobooks. This project does not use its speech-to-text (STT) or other unrelated features.

Disclaimer

• This project is a local-first "ebook to audiobook" tool, intended for converting ebook content that you have the legal right to use into audio.
• Speech synthesis uses third-party voice technology (Microsoft Edge TTS); generating audio requires sending the relevant text to that speech synthesis service.
• You must ensure that you hold the legal right to use any EPUB / TXT content you upload, and you are responsible for that content and its use.
• You may not use this project for any illegal or infringing activity, or in any way that violates third-party terms of service.
• You are responsible for the audio you generate and for any subsequent use of it; the developer of this project does not claim copyright over content you upload.
• Third-party voice services may change, be interrupted, or impose limits, and this project makes no guarantee regarding them.

Privacy

Your library, reading progress, and generated audio can be stored locally in your browser (IndexedDB), with no account required. When generating speech, chapter text must be sent to the speech synthesis service in use (Microsoft Edge TTS) for synthesis. Please do not upload content that contains sensitive personal information you do not want to leave your device.

License

This project is open source under the MIT License; see the LICENSE file in the project root. The core TTS speech synthesis logic retains the MIT License information of the open-source project wangwangit/tts.

Third-party open source software

This website uses FFmpeg WebAssembly components for M4B audio processing. The version currently in use, @ffmpeg/core@0.12.9 (including ffmpeg-core.js and ffmpeg-core.wasm), is released under the GPL-2.0-or-later license. The full list of third-party components and licenses is documented in the project's THIRD-PARTY-NOTICES.md.

• GPL-2.0-or-later license text: https://www.gnu.org/licenses/gpl-2.0.html
• @ffmpeg/core official repository: https://github.com/ffmpegwasm/ffmpeg.wasm
• FFmpeg official project: https://ffmpeg.org/
• FFmpeg official source repository: https://git.ffmpeg.org/ffmpeg.git

This project uses the WebAssembly files from the official npm release of @ffmpeg/core@0.12.9. That release corresponds to release tag v12.14 of the official repository (ffmpegwasm/ffmpeg.wasm), whose official build recipe (Dockerfile) records the FFmpeg source version as tag n5.1.4 (no specific commit is provided officially).