demand
There are many articles on the Internet that convert manuscripts to videos, but they often rely on large models such as Stable Diffusion (such as link), which are not easy to deploy and use. Therefore, I plan to make an article-to-video tool based on Python and open-source libraries to easily convert illustrated web articles into videos.
The code has been uploaded to GitHub: github.com/sim4d/text2...
Specific steps:
- Get the content of the article via requests
- 借 edge-tts 生成语音及字幕
- 利用 BeautifulSoap 抓取文章图像
- Then use MoviePy to stitch images into video and match voice and subtitles
Project features:
- 完全基于 Python 及其第三方应用库,无需依赖于stable-diffusion/midjourney等大模型。
- Taking the WeChat official account article as an example, the specific query of the function is based on the characteristics of the official account article (such as the get_title / get_wechat_article functions in make_audio.py). If you use it for other types of articles, you may need to adjust the tag and class information of the query
Development environment
Windows 11, WSL2 + Rocky 9.3,Python 3.12
安装 Rocky Linux 9.3 for Windows Subsystem for Linux 2 (WSL2), refer to link
wget -Uri https://dl.rockylinux.org/pub/rocky/9/images/x86_64/Rocky-9-Container-Base.latest.x86_64.tar.xz -OutFile ./Rocky-9-Container-Base.latest.x86_64.tar.xz
mkdir wsl-rocky
wsl --import rocky9 ./wsl-rocky ./Rocky-9-Container-Base.latest.x86_64.tar.xz --version 2
wsl -d rocky9
Upgrade the system and add regular users
# dnf install epel-release
# dnf update && dnf upgrade
#
# dnf install sudo
# adduser wsl
# passwd wsl
# usermod -aG wheel wsl
# exit
Enter Rocky9 as a normal user
wsl -d rocky9 -u wsl
安装 pip 和 ImageMagick
sudo dnf install python3-pip
sudo dnf install ImageMagick
sudo dnf install git vim
准备 sandbox (要求 pub key 已经在 GitHub 账户 Profile 设置好)
cd ~/
mkdir sandbox
cd sandbox
git clone [email protected]:sim4d/text2video.git text2video
Install dependencies
cd ~/sandbox/text2video
python3 -m venv my_venv
source ./my_venv/bin/activate
pip3 install -r requirements.txt
Set the URL and run the text2video.py
python3 text2video.py
References
- zulko.github.io/moviepy/ref…
- github.com/rany2/edge-…
Miscellaneous
1. edge-tts 生成 vtt 字幕时,只能以词语为 Boundary
Once the video is made, the subtitles look messy. As shown in Fig
solution
把 edge-tts 项目导入进来,并打上patch,改为以句子为 Boundary
Patch diff
$ diff -u communicate.py-original communicate.py
--- communicate.py-original 2024-05-12 16:28:58.031623420 +0800
+++ communicate.py 2024-05-13 00:20:53.785773846 +0800
@@ -331,7 +331,7 @@
"Content-Type:application/json; charset=utf-8\r\n"
"Path:speech.config\r\n\r\n"
'{"context":{"synthesis":{"audio":{"metadataoptions":{'
- '"sentenceBoundaryEnabled":false,"wordBoundaryEnabled":true},'
+ '"sentenceBoundaryEnabled":true,"wordBoundaryEnabled":false},'
'"outputFormat":"audio-24khz-48kbitrate-mono-mp3"'
"}}}}\r\n"
)
@@ -359,7 +359,7 @@
def parse_metadata() -> Dict[str, Any]:
for meta_obj in json.loads(data)["Metadata"]:
meta_type = meta_obj["Type"]
- if meta_type == "WordBoundary":
+ if meta_type in ("WordBoundary", "SentenceBoundary"):
current_offset = meta_obj["Data"]["Offset"] + offset_compensation
current_duration = meta_obj["Data"]["Duration"]
return {
New subtitle effects
2. With the same code, using WSL + Ubuntu, you will encounter the following problems. It's the same with Ubuntu 24.04. In the end, switch to Rocky 9.3.
Traceback (most recent call last):
File "/home/wsl/sandbox/text2video/text2video.py", line 116, in <module>
main(url, font_path)
File "/home/wsl/sandbox/text2video/text2video.py", line 107, in main
generate_video(images_dir, audio_path, vtt_path, font_path, output_path, front_txt, title_txt)
File "/home/wsl/sandbox/text2video/text2video.py", line 36, in generate_video
front_clip = mp.TextClip(front_txt, color='black', bg_color='white', font=font_path, align='West', kerning=5, fontsize=18)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/home/wsl/sandbox/text2video/my_venv/lib/python3.12/site-packages/moviepy/video/VideoClip.py", line 1146, in __init__
raise IOError(error)
OSError: MoviePy Error: creation of None failed because of the following error:
convert-im6.q16: attempt to perform an operation not allowed by the security policy `@/tmp/tmpn53ke08b.txt' @ error/property.c/InterpretImageProperties/3771.
convert-im6.q16: label expected `@/tmp/tmpn53ke08b.txt' @ error/annotate.c/GetMultilineTypeMetrics/782.
convert-im6.q16: no images defined `PNG32:/tmp/tmp3vlxrrq6.png' @ error/convert.c/ConvertImageCommand/3234.
.
.This error can be due to the fact that ImageMagick is not installed on your computer, or (for Windows users) that you didn't specify the path to the ImageMagick binary in file conf.py, or that the path you specified is incorrect
solution
This may be a problem specific to Windows + Python + ImageMagick, as if this link ran into a similar issue and successfully resolved.
作者:Simford
Link: https://juejin.cn/post/7368637177428426752
Source: Rare Earth Nuggets