在Swift中，我如何在text to speech中使用字符串进行1-5秒的小停顿？

import AVFoundation

func speakWithPauses(text: String) {
    // 创建一个AVSpeechUtterance实例
    let utterance = AVSpeechUtterance(string: text)
    
    // 设置语言
    utterance.voice = AVSpeechSynthesisVoice(language: "en-US")
    
    // 使用SSML来添加停顿
    let ssmlText = """
    <speak>
        Hello, this is a test.
        <break time="1s"/> // 1秒停顿
        Now, let's try a longer pause.
        <break time="5s"/> // 5秒停顿
        That was a five-second pause.
    </speak>
    """
    
    // 将SSML文本转换为NSAttributedString
    let attributedString = NSAttributedString(string: ssmlText, attributes: [.xml: "true"])
    utterance.attributedText = attributedString
    
    // 获取AVSpeechSynthesizer实例并开始说话
    let synthesizer = AVSpeechSynthesizer()
    synthesizer.speak(utterance)
}

// 调用函数
speakWithPauses(text: "")