https://github.com/harry0703/MoneyPrinterTurbo

cd  /data/site/htmltoo.opt

git clone https://github.com/harry0703/MoneyPrinterTurbo.git

cd MoneyPrinterTurbo

conda create -n MoneyPrinterTurbo python=3.11 -y

conda activate MoneyPrinterTurbo

pip install -r requirements.txt

-

apt-get install -y imagemagick

# 媒体编解码器

apt install -y ubuntu-restricted-extras

-多媒体视频处理工具

apt install -y ffmpeg

apt install -y speech-dispatcher

-启动Web界面 

nohup  sh webui.sh > webui.log   2>&1 &

sh webui.sh

-启动API服务

nohup  python main.py  --listen 0.0.0.0 > main.log   2>&1 &

-启动成功后，修改 config.toml 中的配置

llm_provider 设置为 openai

openai_api_key 随便填写一个即可，比如 '123456'

openai_base_url 改为 http://192.168.1.11:3040/v1/

openai_model_name 改为 gpt-3.5-turbo

-

https://www.pexels.com/zh-cn/

https://www.pexels.com/api/key/

key：

mRUgPAan9mRxpmgTbj7pawBumN0u4AY5OtNn6uKionBtQOqMH4Lpe2Cw

模型下载后解压，整个目录放到 .\MoneyPrinterTurbo\models 里面， 

最终的文件路径应该是这样: .\MoneyPrinterTurbo\models\whisper-large-v3

-ImageMagick的安全策略

/etc/ImageMagick-6/policy.xml

rights="none"  ---> rights="read|write"

-

vim  app/config/config.py

listen_port = _cfg.get("listen_port", 8081)