Convert Ebooks to Audiobooks with [custom] voice samples
Project description
Kenkui
Kenkui is basically a fancy wrapper for Kyutai's pocket-tts, with support for ebook parsing. It is multithreaded, and runs faster than any other tool I've used, so I figured I'd start a project to make it easier to use.
Features
- Freaky fast audiobook generation
- No GPU needed, 100% cpu
- Super High Quality Text-to-Speech
- State of the Art Tools
- Multithreaded
- Custom voices
- Chapter selection
- Batch processing
Requirements
- python
- pip, pipx, or uv
- ffmpeg
Quick Start
Dependencies:
uv tool install kenkui
kenkui <your ebook name>.epub
You can also install using pip or pipx!
pip install kenkui
pipx install kenkui
Usage
You can pass a file or directory into kenkui, and it will search directories recursively for .epub files and convert them to m4b files.
Use --voice to specify the voice you want to use.
- accepts:
- the six default voices of pocket-tts (alba, marius, javert, jean, fantine, cosette, eponine, azelma)
- .wav files locally on computer (kenkui ships with quite a few extra)
- voices and safetensor files from hugging face (starts with hf://)
Use --list-voices to see all of the voices kenkui ships with.
Use --select-chapters and --select-books to specify which chapters or books
you want to use.
[!NOTE] go to kyutai's official website to try the default voices out!
Custom voices
In order to use your own custom voice, make sure to record a 5-10 second clip of the person speaking, with minimal background noise or crosstalk. We highly recommend using some sort of tool to clean the audio.
Examples
kenkui book.epub
kenkui library/ --select-books --voice alba
kenkui book.epub -o output/ -j 4
kenkui book.epub --select-chapters --voice ~/Downloads/voice.wav
Notes
At this time we do not plan on supporting mp3, not because it's hard, but because m4b is a wonderful format. There is also currently not support for ebook formats other than epub. I'm sure it'll get added in the future.
For similar reasons, currently only pocket-tts is supported as the tts provider. It's the smallest, fastest, and most feature complete at the moment.
Special Thanks
Thank you to the Guttenberg Project for providing some books included in kenkui!
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Filter files by name, interpreter, ABI, and platform.
If you're not sure about the file name format, learn more about wheel file names.
Copy a direct link to the current filters
File details
Details for the file kenkui-0.3.3.tar.gz.
File metadata
- Download URL: kenkui-0.3.3.tar.gz
- Upload date:
- Size: 50.6 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.27 {"installer":{"name":"uv","version":"0.9.27","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
1e4b3a93f56b3d33a51d4850302b79babb99ca902fef003600062c5b7cc43b90
|
|
| MD5 |
fee3474ce82790e4d883f274bc888b20
|
|
| BLAKE2b-256 |
4cab2e355524861d85c166e1256212da872e2caf7d4d160ec540c99cae82d788
|
File details
Details for the file kenkui-0.3.3-py3-none-any.whl.
File metadata
- Download URL: kenkui-0.3.3-py3-none-any.whl
- Upload date:
- Size: 38.8 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: uv/0.9.27 {"installer":{"name":"uv","version":"0.9.27","subcommand":["publish"]},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 |
83b9ab34b20aba1a7b33b68f881a0963d2ebadae95ef9daf84cee700b12ee9d4
|
|
| MD5 |
ec0bf8fe8a570758259ccb2784932d47
|
|
| BLAKE2b-256 |
112e524b53edc3ab041d3485e0bac7abae413d0f4e83b5b2e76de4f0373dbbe9
|
