使用Azure合成语音，解放嘴巴（bushi）

首先去微软申请以下azure语音的api

不同的语音风格可在参考此处：
https://learn.microsoft.com/zh-cn/azure/ai-services/speech-service/language-support?tabs=tts

pip install azure-cognitiveservices-speech

import azure.cognitiveservices.speech as speechsdk
import os
# 设置你的Azure语音服务的密钥和区域
speech_key = "xxx"
service_region = "eastasia"

def synthesize_speech(text):
    output_dir = "./speech"
    os.makedirs(output_dir, exist_ok=True)
    
    # 生成文件路径
    output_file = os.path.join(output_dir, f"{text}.mp3")
    # 创建语音配置对象
    speech_config = speechsdk.SpeechConfig(subscription=speech_key, region=service_region)
    speech_config.speech_synthesis_voice_name = "zh-CN-YunjianNeural" # 选择不同的角色
    
    # 设置输出音频文件
    audio_output = speechsdk.audio.AudioOutputConfig(filename=output_file)
    
    # 创建语音合成器对象
    speech_synthesizer = speechsdk.SpeechSynthesizer(speech_config=speech_config, audio_config=audio_output)
    
    # 合成语音
    result = speech_synthesizer.speak_text_async(text).get()
    
    # 检查结果
    if result.reason == speechsdk.ResultReason.SynthesizingAudioCompleted:
        print(f"语音合成成功，已保存至 {output_file}")
    elif result.reason == speechsdk.ResultReason.Canceled:
        cancellation_details = result.cancellation_details
        print(f"语音合成失败: {cancellation_details.reason}")
        if cancellation_details.reason == speechsdk.CancellationReason.Error:
            print(f"错误详情: {cancellation_details.error_details}")
            
    return f"./speech/{text}.mp3"

这样就生成mp3文件。

可用于manim, janim等视频制作