[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-72044":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":9,"htmlUrl":10,"language":11,"languages":10,"totalLinesOfCode":10,"stars":12,"forks":13,"watchers":14,"openIssues":15,"contributorsCount":16,"subscribersCount":16,"size":16,"stars1d":17,"stars7d":18,"stars30d":19,"stars90d":16,"forks30d":16,"starsTrendScore":20,"compositeScore":21,"rankGlobal":10,"rankLanguage":10,"license":22,"archived":23,"fork":23,"defaultBranch":24,"hasWiki":23,"hasPages":23,"topics":25,"createdAt":10,"pushedAt":10,"updatedAt":31,"readmeContent":32,"aiSummary":33,"trendingCount":16,"starSnapshotCount":16,"syncStatus":34,"lastSyncTime":35,"discoverSource":36},72044,"audiblez","santinic\u002Faudiblez","santinic","Generate audiobooks from e-books","",null,"Python",7508,630,43,49,0,251,265,312,753,39.4,"MIT License",false,"main",[26,27,28,29,30],"audiobooks","epub","kokoro","python","tts","2026-06-12 02:02:57","# Audiblez: Generate  audiobooks from e-books\n\n[![Installing via pip and running](https:\u002F\u002Fgithub.com\u002Fsantinic\u002Faudiblez\u002Factions\u002Fworkflows\u002Fpip-install.yaml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsantinic\u002Faudiblez\u002Factions\u002Fworkflows\u002Fpip-install.yaml)\n[![Git clone and run](https:\u002F\u002Fgithub.com\u002Fsantinic\u002Faudiblez\u002Factions\u002Fworkflows\u002Fgit-clone-and-run.yml\u002Fbadge.svg)](https:\u002F\u002Fgithub.com\u002Fsantinic\u002Faudiblez\u002Factions\u002Fworkflows\u002Fgit-clone-and-run.yml)\n![PyPI - Python Version](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fpyversions\u002Faudiblez)\n![PyPI - Version](https:\u002F\u002Fimg.shields.io\u002Fpypi\u002Fv\u002Faudiblez)\n\n### v4 Now with Graphical interface, CUDA support, and many languages!\n\n![Audiblez GUI on MacOSX](.\u002Fimgs\u002Fmac.png)\n\nAudiblez generates `.m4b` audiobooks from regular `.epub` e-books,\nusing Kokoro's high-quality speech synthesis.\n\n[Kokoro-82M](https:\u002F\u002Fhuggingface.co\u002Fhexgrad\u002FKokoro-82M) is a recently published text-to-speech model with just 82M params and very natural sounding output.\nIt's released under Apache licence and it was trained on \u003C 100 hours of audio.\nIt currently supports these languages: 🇺🇸 🇬🇧 🇪🇸 🇫🇷 🇮🇳 🇮🇹 🇯🇵 🇧🇷 🇨🇳\n\nOn a Google Colab's T4 GPU via Cuda, **it takes about 5 minutes to convert \"Animal's Farm\" by Orwell** (which is about 160,000 characters) to audiobook, at a rate of about 600 characters per second.\n\nOn my M2 MacBook Pro, on CPU, it takes about 1 hour, at a rate of about 60 characters per second.\n\n\n## How to install the Command Line tool\n\nIf you have Python 3 on your computer, you can install it with pip.\nYou also need `espeak-ng` and `ffmpeg` installed on your machine:\n\n```bash\nsudo apt install ffmpeg espeak-ng                   # on Ubuntu\u002FDebian 🐧\npip install audiblez\n```\n\n```bash\nbrew install ffmpeg espeak-ng                       # on Mac 🍏\npip install audiblez\n```\n\nThen you can convert an .epub directly with:\n\n```\naudiblez book.epub -v af_sky\n```\n\nIt will first create a bunch of `book_chapter_1.wav`, `book_chapter_2.wav`, etc. files in the same directory,\nand at the end it will produce a `book.m4b` file with the whole book you can listen with VLC or any\naudiobook player.\nIt will only produce the `.m4b` file if you have `ffmpeg` installed on your machine.\n\n## How to run the GUI\n\nThe GUI is a simple graphical interface to use audiblez.\nYou need some extra dependencies to run the GUI:\n\n```\nsudo apt install ffmpeg espeak-ng \nsudo apt install libgtk-3-dev        # just for Ubuntu\u002FDebian 🐧, Windows\u002FMac don't need this\n  \npip install audiblez pillow wxpython\n```\n\nThen you can run the GUI with:\n```\naudiblez-ui\n```\n\n## How to run on Windows\n\nAfter many trials, on Windows we recommend to install audiblez in a Python venv:\n\n1. Open a Windows terminal\n2. Create anew folder: `mkdir audiblez`\n3. Enter the folder: `cd audiblez`\n4. Create a venv: `python -m venv venv`\n5. Activate the venv: `.\\venv\\Scripts\\Activate.ps1`\n6. Install the dependencies: `pip install audiblez pillow wxpython`\n7. Now you can run `audiblez` or `audiblez-ui`\n8. For Cuda support, you need to install Pytorch accordingly: https:\u002F\u002Fpytorch.org\u002Fget-started\u002Flocally\u002F\n\n\n## Speed\n\nBy default the audio is generated using a normal speed, but you can make it up to twice slower or faster by specifying a speed argument between 0.5 to 2.0:\n\n```\naudiblez book.epub -v af_sky -s 1.5\n```\n\n## Supported Voices\n\nUse `-v` option to specify the voice to use. Available voices are listed here.\nThe first letter is the language code and the second is the gender of the speaker e.g. `im_nicola` is an italian male voice.\n\n[For hearing samples of Kokoro-82M voices, go here](https:\u002F\u002Fclaudio.uk\u002Fposts\u002Faudiblez-v4.html)\n\n| Language                  | Voices                                                                                                                                                                                                                                     |\n|---------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|\n| 🇺🇸 American English     | `af_alloy`, `af_aoede`, `af_bella`, `af_heart`, `af_jessica`, `af_kore`, `af_nicole`, `af_nova`, `af_river`, `af_sarah`, `af_sky`, `am_adam`, `am_echo`, `am_eric`, `am_fenrir`, `am_liam`, `am_michael`, `am_onyx`, `am_puck`, `am_santa` |\n| 🇬🇧 British English      | `bf_alice`, `bf_emma`, `bf_isabella`, `bf_lily`, `bm_daniel`, `bm_fable`, `bm_george`, `bm_lewis`                                                                                                                                          |\n| 🇪🇸 Spanish              | `ef_dora`, `em_alex`, `em_santa`                                                                                                                                                                                                           |\n| 🇫🇷 French               | `ff_siwis`                                                                                                                                                                                                                                 |\n| 🇮🇳 Hindi                | `hf_alpha`, `hf_beta`, `hm_omega`, `hm_psi`                                                                                                                                                                                                |\n| 🇮🇹 Italian              | `if_sara`, `im_nicola`                                                                                                                                                                                                                     |\n| 🇯🇵 Japanese             | `jf_alpha`, `jf_gongitsune`, `jf_nezumi`, `jf_tebukuro`, `jm_kumo`                                                                                                                                                                         |\n| 🇧🇷 Brazilian Portuguese | `pf_dora`, `pm_alex`, `pm_santa`                                                                                                                                                                                                           |\n| 🇨🇳 Mandarin Chinese     | `zf_xiaobei`, `zf_xiaoni`, `zf_xiaoxiao`, `zf_xiaoyi`, `zm_yunjian`, `zm_yunxi`, `zm_yunxia`, `zm_yunyang`                                                                                                                                 |\n\nFor more detaila about voice quality, check this document: [Kokoro-82M voices](https:\u002F\u002Fhuggingface.co\u002Fhexgrad\u002FKokoro-82M\u002Fblob\u002Fmain\u002FVOICES.md)\n\n## How to run on GPU\n\nBy default, audiblez runs on CPU. If you pass the option `--cuda` it will try to use the Cuda device via Torch.\n\nCheck out this example: [Audiblez running on a Google Colab Notebook with Cuda ](https:\u002F\u002Fcolab.research.google.com\u002Fdrive\u002F164PQLowogprWQpRjKk33e-8IORAvqXKI?usp=sharing]).\n\nWe don't currently support Apple Silicon, as there is not yet a Kokoro implementation in MLX. As soon as it will be available, we will support it.\n\n## Manually pick chapters to convert\n\nSometimes you want to manually select which chapters\u002Fsections in the e-book to read out loud.\nTo do so, you can use `--pick` to interactively choose the chapters to convert (without running the GUI).\n\n\n## Help page\n\nFor all the options available, you can check the help page `audiblez --help`:\n\n```\nusage: audiblez [-h] [-v VOICE] [-p] [-s SPEED] [-c] [-o FOLDER] epub_file_path\n\npositional arguments:\n  epub_file_path        Path to the epub file\n\noptions:\n  -h, --help            show this help message and exit\n  -v VOICE, --voice VOICE\n                        Choose narrating voice: a, b, e, f, h, i, j, p, z\n  -p, --pick            Interactively select which chapters to read in the audiobook\n  -s SPEED, --speed SPEED\n                        Set speed from 0.5 to 2.0\n  -c, --cuda            Use GPU via Cuda in Torch if available\n  -o FOLDER, --output FOLDER\n                        Output folder for the audiobook and temporary files\n\nexample:\n  audiblez book.epub -l en-us -v af_sky\n\nto use the GUI, run:\n  audiblez-ui\n```\n\n## Author\n\nby [Claudio Santini](https:\u002F\u002Fclaudio.uk) in 2025, distributed under MIT licence.\n\nRelated Article: [Audiblez v4: Generate Audiobooks from E-books](https:\u002F\u002Fclaudio.uk\u002Fposts\u002Faudiblez-v4.html)\n","Audiblez 是一个能够将电子书（如 EPUB 格式）转换为有声书的工具。它基于 Python 开发，使用了高质量的语音合成技术 Kokoro-82M，支持多种语言，包括英语、西班牙语、法语等，并且提供了图形界面和 CUDA 加速功能。Audiblez 适用于需要将文本内容转化为音频格式的场景，比如个人学习、阅读障碍者辅助或是内容创作者希望扩大其作品的受众范围。在配备适当硬件的情况下，该工具可以高效地完成转换任务，例如在 T4 GPU 上仅需约5分钟即可处理完一本中等长度的书籍。",2,"2026-06-11 03:40:07","high_star"]