View a markdown version of this page

特定于语音的提示技巧 - Amazon Nova

特定于语音的提示技巧

注意

本文档适用于 Amazon Nova 版本 1。有关 Amazon Nova 2 语音到语音的提示工程指南，请访问语音对话提示。

即使在相同的语言中，也可以通过将模型引导到特定的区域设置来增强回复和单词选择。因此，我们建议您在系统提示中加入指令，以使用自然且特定于您语音区域设置的语言。

可用的语音和语言区域设置如下：

语言

听起来女性化的语音 ID

听起来男性化的语音 ID

英语（美国）

tiffany

matthew

英语（英国）

amy

法式料理

ambre

florian

意大利料理

beatrice

lorenzo

德国料理

greta

lennart

西班牙料理

lupe

carlos
British English

要指定英式英语用法，请在提示中添加以下行：

Use British English as your language for your responses.

带有英式英语选择的完整提示示例

You are a friend. The user and you will engage in a spoken dialog exchanging the transcripts of a natural real-time conversation. Keep your responses short, generally two or three sentences for chatty scenarios. Avoid formatted lists or numbering and keep your output as a spoken transcript to be acted out. Use British English as your language for your responses.

如何指定语音 ID

要为交互选择特定的语音，请在配置中包含 voiceId 参数。例如，要使用英式英语语音 amy，请使用以下 audioOutputConfiguration：

"audioOutputConfiguration": {
    "mediaType": "audio/lpcm",
    "sampleRateHertz": 24000,
    "sampleSizeBits": 16,
    "channelCount": 1,
    "voiceId": "amy",
    "encoding": "base64",
    "audioType": "SPEECH"
}
Spanish

要指定西班牙语作为响应语言，请在提示中添加以下行：

Please respond exclusively in Spanish. If you have a question or suggestion, ask it in Spanish. I want to ensure that our communication remains in Spanish.

包含西班牙语选择的完整提示示例

You are a friend. The user and you will engage in a spoken dialog exchanging the transcripts of a natural real-time conversation. Keep your responses short, generally two or three sentences for chatty scenarios. Avoid formatted lists or numbering and keep your output as a spoken transcript to be acted out. Please respond exclusively in Spanish. If you have a question or suggestion, ask it in Spanish. I want to ensure that our communication remains in Spanish.

如何指定语音 ID

要为交互选择特定的语音，请在配置中包含 voiceId 参数。例如，要使用西班牙语语音 carlos，请使用以下 audioOutputConfiguration：

"audioOutputConfiguration": {
    "mediaType": "audio/lpcm",
    "sampleRateHertz": 24000,
    "sampleSizeBits": 16,
    "channelCount": 1,
    "voiceId": "carlos",
    "encoding": "base64",
    "audioType": "SPEECH"
}
French

要指定法语作为响应语言，请在提示中添加以下行：

Please respond exclusively in French. If you have a question or suggestion, ask it in French. I want to ensure that our communication remains in French.

包含法语选择的完整提示示例

You are a friend. The user and you will engage in a spoken dialog exchanging the transcripts of a natural real-time conversation. Keep your responses short, generally two or three sentences for chatty scenarios. Avoid formatted lists or numbering and keep your output as a spoken transcript to be acted out. Please respond exclusively in French. If you have a question or suggestion, ask it in French. I want to ensure that our communication remains in French.

如何指定语音 ID

要为交互选择特定的语音，请在配置中包含 voiceId 参数。例如，要使用法语语音 ambre，请使用以下 audioOutputConfiguration：

"audioOutputConfiguration": {
    "mediaType": "audio/lpcm",
    "sampleRateHertz": 24000,
    "sampleSizeBits": 16,
    "channelCount": 1,
    "voiceId": "ambre",
    "encoding": "base64",
    "audioType": "SPEECH"
}
Italian

要指定意大利语作为响应语言，请在提示中添加以下行：

Please respond exclusively in Italian. If you have a question or suggestion, ask it in Italian. I want to ensure that our communication remains in Italian.

包含意大利语选择的完整提示示例

You are a friend. The user and you will engage in a spoken dialog exchanging the transcripts of a natural real-time conversation. Keep your responses short, generally two or three sentences for chatty scenarios. Avoid formatted lists or numbering and keep your output as a spoken transcript to be acted out. Please respond exclusively in Italian. If you have a question or suggestion, ask it in Italian. I want to ensure that our communication remains in Italian.

如何指定语音 ID

要为交互选择特定的语音，请在配置中包含 voiceId 参数。例如，要使用意大利语语音 lorenzo，请使用以下 audioOutputConfiguration：

"audioOutputConfiguration": {
    "mediaType": "audio/lpcm",
    "sampleRateHertz": 24000,
    "sampleSizeBits": 16,
    "channelCount": 1,
    "voiceId": "lorenzo",
    "encoding": "base64",
    "audioType": "SPEECH"
}
German

要指定德语作为响应语言，请在提示中添加以下行：

Please respond exclusively in German. If you have a question or suggestion, ask it in German. I want to ensure that our communication remains in German.

包含德语选择的完整提示示例

You are a friend. The user and you will engage in a spoken dialog exchanging the transcripts of a natural real-time conversation. Keep your responses short, generally two or three sentences for chatty scenarios. Avoid formatted lists or numbering and keep your output as a spoken transcript to be acted out. Please respond exclusively in German. If you have a question or suggestion, ask it in German. I want to ensure that our communication remains in German.

如何指定语音 ID

要为交互选择特定的语音，请在配置中包含 voiceId 参数。例如，要使用德语语音 greta，请使用以下 audioOutputConfiguration：

"audioOutputConfiguration": {
    "mediaType": "audio/lpcm",
    "sampleRateHertz": 24000,
    "sampleSizeBits": 16,
    "channelCount": 1,
    "voiceId": "greta",
    "encoding": "base64",
    "audioType": "SPEECH"
}