1、wsay
Reference:
https://github.com/p-groarke/wsay
Download and install:
https://github.com/p-groarke/wsay/releases/tag/v1.5.0
Download the exe file and add it to the environment variable
use
# Say something.
wsay "Hello there."
wsay "你好"
Video_20230813075925
2、puddlex3
Reference:
https://zhuanlan.zhihu.com/p/507369886
https://blog.51cto.com/u_12891/6705605
Install:
pip install pyttsx3 -i https://pypi.tuna.tsinghua.edu.cn/simple --user
Usage:
Call pyttsx3.speak() directly
import pyttsx3
#语音播放
pyttsx3.speak("How are you?")
pyttsx3.speak("I am fine, thank you")
pyttsx3.speak("具体来说,这个命令中的参数-NL表示创建本地端口转发。它将本地机器的7860端口与远程服务器的192.168.19.14:7860端口进行连接。实际上,当本地机器收到对本地7860端口的请求时,请求将被转发到远程服务器的192.168.19.14:7860端口。通过这个隧道建立的通信是安全的,因为SSH使用了加密来保护数据的传输。这意味着在本地机器和远程服务器之间传输的数据被加密,只有具有正确密钥的两端才能解密和读取数据。在隧道建立后,您可以在本地机器上通过访问localhost:7860来与远程服务器上的服务进行通信。本地机器上的请求会被转发到远程服务器,并得到响应。这样,您可以通过安全的通道在本地机器和远程服务器之间进行通信。")
3. Microsoft edge-tts sound is naturally offline and not real-time
Reference: https://github.com/rany2/edge-tts
Installation:
pip install edge-tts
use:
edge-tts --text "Hello, world!" --write-media hello.mp3 --write-subtitles hello.vtt
Specify language tone selection:
edge-tts --list-voices ##查看支持的
edge-tts --voice ar-EG-SalmaNeural ##添加 --voice
If you want sound broadcast, you need to install the mpv command line video playback tool, download: https://mpv.io/installation/
After downloading the windows zip file and compressing it, you need to add the path to the environment variable.
After installation, you can play sounds from the command line:
The playback speed will be relatively delayed, which is equivalent to converting the text into a voice mp3 file first, and then playing the mp3 file; the advantage is that the sound quality is great and close to real people.
edge-playback --text "Hello, world!"
edge-playback --text "这个错误表明在尝试进行SSL连接时,出现了证书验证问题。具体来说,问题出在证书验证过程中,证书验证失败的原因是" --voice zh-CN-XiaoxiaoNeural
If an SSL error is reported here, refer to https://github.com/rany2/edge-tts/issues/110. Change the SSL file in the edge-tts report, mainly in C:\Us****p\Lib\ Change and add in the list_voices.py and communicate.py files under the site-packages\edge_tts path; then run edge-playback to play the sound command.
verify_ssl=False,