添加呼吸音

PDF

RSS

聚焦模式

添加呼吸音 - Amazon Polly

<amazon:breath> 和 <amazon:auto-breaths>

只有标准 TTS 格式支持此标签。

自然声音语音包括正确说出的字词和呼吸音。通过向合成语音添加呼吸音，可以使合成语音听起来更自然。<amazon:breath> 和 <amazon:auto-breaths> 标签可提供呼吸。您有以下选项：

手动模式：您可以在文本中设置呼吸音的位置、长度和音量
自动模式：Amazon Polly 自动将呼吸音插入语音输出
混合模式：由您和 Amazon Polly 共同添加呼吸音

手动模式

在手动模式下，可将 <amazon:breath/> 标签放在要插入呼吸的输入文本中。您可以分别使用 duration 和 volume 属性自定义呼吸的长度和音量：

duration：控制呼吸的长度。有效值为: default, x-short, short, medium, long, x-long。默认值为 medium。
volume：控制呼吸音有多大声。有效值为: default, x-soft, soft, medium, loud, x-loud。默认值为 medium。

注意

每个属性值的确切长度和音量取决于使用的具体 Amazon Polly 语音。

要使用默认值设置呼吸音，请不带属性使用 <amazon:breath/>。

例如，要使用属性将呼吸的持续时间和音量设置为中等，可以按如下方式设置属性：


<speak>
     Sometimes you want to insert only <amazon:breath duration="medium" volume="x-loud"/>a single breath.
</speak>

要使用默认值，只需使用标签：


<speak>
     Sometimes you need <amazon:breath/>to insert one or more average breaths <amazon:breath/> so that the 
     text sounds correct.
</speak>

您可以在一个段落内添加个别呼吸音，如下所示：


<speak>
     <amazon:breath duration="long" volume="x-loud"/> <prosody rate="120%"> <prosody volume="loud"> 
     Wow! <amazon:breath duration="long" volume="loud"/> </prosody> That was quite fast. <amazon:breath 
     duration="medium" volume="x-loud"/> I almost beat my personal best time on this track. </prosody>
</speak>

自动模式

在自动模式下，您使用 <amazon:auto-breaths> 标签来告知 Amazon Polly 以适当的时间间隔自动产生呼吸音。您可以设置间隔的频率、音量和持续时间。将 </amazon:auto-breaths> 标签放在要应用自动呼吸的文本的开头，然后将结束标签放在文本末尾。

注意

与手动模式标签 <amazon:breath/> 不同，<amazon:auto-breaths> 标签必须具有结束标签 (</amazon:auto-breaths>)。

您可以将以下可选属性与 <amazon:auto-breaths> 标签结合使用：

volume：控制呼吸音有多大声。有效值为: default, x-soft, soft, medium, loud, x-loud。默认值为 medium。
frequency：控制文本中出现呼吸音的频率。有效值为: default, x-low, low, medium, high, x-high。默认值为 medium。
duration：控制呼吸的长度。有效值为: default, x-short, short, medium, long, x-long。默认值为 medium。

默认情况下，呼吸音的频率取决于输入文本。但是，呼吸音通常发生在逗号和句点之后。

以下示例显示如何使用 <amazon:auto-breaths> 标签。要确定对您的内容使用哪些选项，请将适用的示例复制到 Amazon Polly 控制台并听其中的差异。

不带可选参数使用自动化模式。


<speak>
     <amazon:auto-breaths>Amazon Polly is a service that turns text into lifelike speech, 
     allowing you to create applications that talk and build entirely new categories of speech-
     enabled products. Amazon Polly is a text-to-speech service that uses advanced deep learning 
     technologies to synthesize speech that sounds like a human voice. With dozens of lifelike 
     voices across a variety of languages, you can select the ideal voice and build speech-
     enabled applications that work in many different countries.</amazon:auto-breaths>
</speak>

将自动化模式与音量控制结合使用。未指定的参数 (duration 和 frequency) 设置为默认值 (medium)。


<speak>
     <amazon:auto-breaths volume="x-soft">Amazon Polly is a service that turns text into lifelike 
     speech, allowing you to create applications that talk and build entirely new categories of 
     speech-enabled products. Amazon Polly is a text-to-speech service, that uses advanced deep 
     learning technologies to synthesize speech that sounds like a human voice. With dozens of 
     lifelike voices across a variety of languages, you can select the ideal voice and build speech-
     enabled applications that work in many different countries.</amazon:auto-breaths>
</speak>

将自动化模式与频率控制结合使用。未指定的参数 (duration 和 volume) 设置为默认值 (medium)。


<speak>
     <amazon:auto-breaths frequency="x-low">Amazon Polly is a service that turns text into lifelike 
     speech, allowing you to create applications that talk and build entirely new categories of 
     speech-enabled products. Amazon Polly is a text-to-speech service, that uses advanced deep 
     learning technologies to synthesize speech that sounds like a human voice. With dozens of 
     lifelike voices across a variety of languages, you can select the ideal voice and build speech-
     enabled applications that work in many different countries.</amazon:auto-breaths>
</speak>

将自动化模式与多个参数结合使用。对于未指定的 Duration 参数，Amazon Polly 将使用默认值 (medium)。


<speak>
     <amazon:auto-breaths volume="x-loud" frequency="x-low">Amazon Polly is a service that turns 
     text into lifelike speech, allowing you to create applications that talk and build entirely new 
     categories of speech-enabled products. Amazon Polly is a text-to-speech service, that uses 
     advanced deep learning technologies to synthesize speech that sounds like a human voice. With 
     dozens of lifelike voices across a variety of languages, you can select the ideal voice and build 
     speech-enabled applications that work in many different countries.</amazon:auto-breaths>
</speak>