edge-tts

install

pip install edge-tts

using by command-li

edge-tts --help
edge-tts --text "Hello, world!" --write-media hello.mp3 --write-subtitles hello.vtt
edge-tts --list-voices
Name: zh-CN-XiaoxiaoNeural   Female
Name: zh-CN-XiaoyiNeural   Female
Name: zh-CN-YunjianNeural   Male
Name: zh-CN-YunxiNeural    Male
Name: zh-CN-YunxiaNeural   Male
Name: zh-CN-YunyangNeural  Male
Name: zh-CN-liaoning-XiaobeiNeural   Female
Name: zh-CN-shaanxi-XiaoniNeural  Female
Name: zh-HK-HiuGaaiNeural  Female
Name: zh-HK-HiuMaanNeural  Female
Name: zh-HK-WanLungNeural  Male
Name: zh-TW-HsiaoChenNeural  Female
Name: zh-TW-HsiaoYuNeural  Female
Name: zh-TW-YunJheNeural  Male

edge-tts --rate=+1%   --volume=+1% --pitch=+5Hz  --text "Hello, world!" --write-media hello.mp3 --write-subtitles hello.vtt --voice zh-CN-XiaoxiaoNeural

edge-tts --rate=+1%   --volume=+1% --pitch=+5Hz  --text "静夜思   - 李白 床前明月光，疑是地上霜。举头望明月，低头思故乡。" --write-media jys.mp3 --write-subtitles jys.vtt --voice zh-CN-XiaoxiaoNeural

edge-tts --rate=+1%   --volume=+1% --pitch=+5Hz  --file "静夜思-李白.txt" --write-media jys.mp3 --write-subtitles jys.vtt --voice zh-CN-XiaoxiaoNeural

using by python code

# !/usr/bin/env python3
# -*- coding: utf8 -*
import subprocess
import uuid

import edge_tts
import asyncio

###########
# pip3 install edge_tts  -i https://mirrors.aliyun.com/pypi/simple/
###########


async def text_to_mp3(text, mp3_name):
    tts = edge_tts.Communicate(text=text, voice='zh-CN-XiaoxiaoNeural', rate='+1%', volume='+1%', pitch='+5Hz')
    await tts.save(str(mp3_name))

if __name__ == '__main__':
    text_to_use = 'Stable Diffusion WebUI，简称SD WebUI，是一个基于Gradio库的Stable Diffusion的浏览器界面。 它支持目前主流的开源AI绘画模型，如NovelAi/Stable Diffusion等。 通过SD WebUI，用户可以方便地配置和生成AI绘画作品，实现精细化的创作。'
    asyncio.run(text_to_mp3(text_to_use, "a.mp3"))

附件

静夜思-李白.txt

静夜思   - 李白
床前明月光，疑是地上霜。
举头望明月，低头思故乡。