建立語音音訊檔案

您可以使用 Text-to-Speech，將字詞和句子轉換成自然人類語音的 base64 編碼音訊資料，接著進行解碼，將這些資料轉換成可播放的音訊檔案，例如 MP3。Text-to-Speech API 接受原始文字或語音合成標記語言 (SSML) 的輸入內容。

本文件說明如何使用 Text-to-Speech，根據文字或 SSML 輸入內容建立音訊檔案。如果您不熟悉語音合成或 SSML 等概念，請參閱「Text-to-Speech 基本概念」。

必須先安裝並初始化 Google Cloud CLI，才能按照這些範例操作。如要瞭解如何設定 gcloud CLI，請參閱「進行 TTS 驗證」。

將文字轉換為合成語音音訊

下列程式碼範例示範如何將字串轉換為音訊資料。

您可以透過各種方式設定語音合成的輸出內容，包括選取獨特的語音或調節輸出內容的音調、音量、語速和取樣率。

通訊協定

如需完整資訊，請參閱 text:synthesize API 端點。

如要根據文字內容合成音訊，請向 text:synthesize 端點發出 HTTP POST 要求。在 POST 要求的主體中，請在 voice 設定區段指定要合成的語音類型，在 input 區段的 text 欄位指定要合成的文字，然後在 audioConfig 區段中指定要建立的音訊類型。

下列程式碼片段會將合成要求傳送至 text:synthesize 端點，並將結果儲存成名為 synthesize-text.txt 的檔案。請將 PROJECT_ID 替換為專案 ID。

curl -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "x-goog-user-project: <var>PROJECT_ID</var>" \
  -H "Content-Type: application/json; charset=utf-8" \
  --data "{
    'input':{
      'text':'Android is a mobile operating system developed by Google,
         based on the Linux kernel and designed primarily for
         touchscreen mobile devices such as smartphones and tablets.'
    },
    'voice':{
      'languageCode':'en-gb',
      'name':'en-GB-Standard-A',
      'ssmlGender':'FEMALE'
    },
    'audioConfig':{
      'audioEncoding':'MP3'
    }
  }" "https://texttospeech.googleapis.com/v1/text:synthesize" > synthesize-text.txt

Text-to-Speech API 會以 base64 編碼資料傳回合成的音訊，包含在 JSON 輸出內容中。synthesize-text.txt 檔案中的 JSON 輸出內容看起來會像以下程式碼片段。

{
  "audioContent": "//NExAASCCIIAAhEAGAAEMW4kAYPnwwIKw/BBTpwTvB+IAxIfghUfW.."
}

如要將 Text-to-Speech API 傳回的結果解碼為 MP3 音訊檔案，請從 synthesize-text.txt 檔案所在的目錄執行下列指令。

cat synthesize-text.txt | grep 'audioContent' | \
sed 's|audioContent| |' | tr -d '\n ":{},' > tmp.txt && \
base64 tmp.txt --decode > synthesize-text-audio.mp3 && \
rm tmp.txt

Go

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Go API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。


// SynthesizeText synthesizes plain text and saves the output to outputFile.
func SynthesizeText(w io.Writer, text, outputFile string) error {
	ctx := context.Background()

	client, err := texttospeech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	req := texttospeechpb.SynthesizeSpeechRequest{
		Input: &texttospeechpb.SynthesisInput{
			InputSource: &texttospeechpb.SynthesisInput_Text{Text: text},
		},
		// Note: the voice can also be specified by name.
		// Names of voices can be retrieved with client.ListVoices().
		Voice: &texttospeechpb.VoiceSelectionParams{
			LanguageCode: "en-US",
			SsmlGender:   texttospeechpb.SsmlVoiceGender_FEMALE,
		},
		AudioConfig: &texttospeechpb.AudioConfig{
			AudioEncoding: texttospeechpb.AudioEncoding_MP3,
		},
	}

	resp, err := client.SynthesizeSpeech(ctx, &req)
	if err != nil {
		return err
	}

	err = os.WriteFile(outputFile, resp.AudioContent, 0644)
	if err != nil {
		return err
	}
	fmt.Fprintf(w, "Audio content written to file: %v\n", outputFile)
	return nil
}

Java

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Java API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

/**
 * Demonstrates using the Text to Speech client to synthesize text or ssml.
 *
 * @param text the raw text to be synthesized. (e.g., "Hello there!")
 * @throws Exception on TextToSpeechClient Errors.
 */
public static ByteString synthesizeText(String text) throws Exception {
  // Instantiates a client
  try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
    // Set the text input to be synthesized
    SynthesisInput input = SynthesisInput.newBuilder().setText(text).build();

    // Build the voice request
    VoiceSelectionParams voice =
        VoiceSelectionParams.newBuilder()
            .setLanguageCode("en-US") // languageCode = "en_us"
            .setSsmlGender(SsmlVoiceGender.FEMALE) // ssmlVoiceGender = SsmlVoiceGender.FEMALE
            .build();

    // Select the type of audio file you want returned
    AudioConfig audioConfig =
        AudioConfig.newBuilder()
            .setAudioEncoding(AudioEncoding.MP3) // MP3 audio.
            .build();

    // Perform the text-to-speech request
    SynthesizeSpeechResponse response =
        textToSpeechClient.synthesizeSpeech(input, voice, audioConfig);

    // Get the audio contents from the response
    ByteString audioContents = response.getAudioContent();

    // Write the response to the output file.
    try (OutputStream out = new FileOutputStream("output.mp3")) {
      out.write(audioContents.toByteArray());
      System.out.println("Audio content written to file \"output.mp3\"");
      return audioContents;
    }
  }
}

Node.js

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Node.js API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

const textToSpeech = require('@google-cloud/text-to-speech');
const fs = require('fs');
const util = require('util');

const client = new textToSpeech.TextToSpeechClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const text = 'Text to synthesize, eg. hello';
// const outputFile = 'Local path to save audio file to, e.g. output.mp3';

const request = {
  input: {text: text},
  voice: {languageCode: 'en-US', ssmlGender: 'FEMALE'},
  audioConfig: {audioEncoding: 'MP3'},
};
const [response] = await client.synthesizeSpeech(request);
const writeFile = util.promisify(fs.writeFile);
await writeFile(outputFile, response.audioContent, 'binary');
console.log(`Audio content written to file: ${outputFile}`);

Python

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Python API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

def synthesize_text():
    """Synthesizes speech from the input string of text."""
    from google.cloud import texttospeech

    text = "Hello there."
    client = texttospeech.TextToSpeechClient()

    input_text = texttospeech.SynthesisInput(text=text)

    # Note: the voice can also be specified by name.
    # Names of voices can be retrieved with client.list_voices().
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US",
        name="en-US-Chirp3-HD-Charon",
    )

    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    response = client.synthesize_speech(
        input=input_text,
        voice=voice,
        audio_config=audio_config,
    )

    # The response's audio_content is binary.
    with open("output.mp3", "wb") as out:
        out.write(response.audio_content)
        print('Audio content written to file "output.mp3"')

其他語言

C#：請按照用戶端程式庫頁面的 C# 設定操作說明完成相關步驟，然後參閱 .NET 適用的 Text-to-Speech 參考文件。

PHP：請按照用戶端程式庫頁面的 PHP 設定操作說明完成相關步驟，然後參閱 PHP 適用的 Text-to-Speech 參考文件。

Ruby：請按照用戶端程式庫頁面的 Ruby 設定操作說明完成相關步驟，然後參閱 Ruby 適用的 Text-to-Speech 參考文件。

將 SSML 轉換為合成語音音訊

在音訊合成要求中使用 SSML，產生的音訊會更類似自然人類語音。具體來說，您可以使用 SSML，以更精細的方式控制音訊輸出在說話時如何表示停頓，或音訊如何唸出日期、時間、首字母縮略字及縮寫。

如要進一步瞭解 Text-to-Speech API 支援的 SSML 元素，請參閱 SSML 參考資料。

通訊協定

如需完整資訊，請參閱 text:synthesize API 端點。

如要根據 SSML 合成音訊，請向 text:synthesize 端點發出 HTTP POST 要求。在 POST 要求的主體中，請在 voice 設定區段指定要合成的語音類型，在 input 區段的 ssml 欄位指定要合成的 SSML，然後在 audioConfig 區段中指定要建立的音訊類型。

下列程式碼片段會將合成要求傳送至 text:synthesize 端點，並將結果儲存成名為 synthesize-ssml.txt 的檔案。請將 PROJECT_ID 替換為專案 ID。

curl -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "x-goog-user-project: <var>PROJECT_ID</var>" \
  -H "Content-Type: application/json; charset=utf-8" --data "{
    'input':{
     'ssml':'<speak>The <say-as interpret-as=\"characters\">SSML</say-as> standard
          is defined by the <sub alias=\"World Wide Web Consortium\">W3C</sub>.</speak>'
    },
    'voice':{
      'languageCode':'en-us',
      'name':'en-US-Standard-B',
      'ssmlGender':'MALE'
    },
    'audioConfig':{
      'audioEncoding':'MP3'
    }
  }" "https://texttospeech.googleapis.com/v1/text:synthesize" > synthesize-ssml.txt

Text-to-Speech API 會以 base64 編碼資料傳回合成的音訊，包含在 JSON 輸出內容中。synthesize-ssml.txt 檔案中的 JSON 輸出內容看起來會像以下程式碼片段。

{
  "audioContent": "//NExAASCCIIAAhEAGAAEMW4kAYPnwwIKw/BBTpwTvB+IAxIfghUfW.."
}

如要將 Text-to-Speech API 傳回的結果解碼為 MP3 音訊檔案，請從 synthesize-ssml.txt 檔案所在的目錄執行下列指令。

cat synthesize-ssml.txt | grep 'audioContent' | \
sed 's|audioContent| |' | tr -d '\n ":{},' > tmp.txt && \
base64 tmp.txt --decode > synthesize-ssml-audio.mp3 && \
rm tmp.txt

Go

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Go API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。


// SynthesizeSSML synthesizes ssml and saves the output to outputFile.
//
// ssml must be well-formed according to:
//
//	https://www.w3.org/TR/speech-synthesis/
//
// Example: <speak>Hello there.</speak>
func SynthesizeSSML(w io.Writer, ssml, outputFile string) error {
	ctx := context.Background()

	client, err := texttospeech.NewClient(ctx)
	if err != nil {
		return err
	}
	defer client.Close()

	req := texttospeechpb.SynthesizeSpeechRequest{
		Input: &texttospeechpb.SynthesisInput{
			InputSource: &texttospeechpb.SynthesisInput_Ssml{Ssml: ssml},
		},
		// Note: the voice can also be specified by name.
		// Names of voices can be retrieved with client.ListVoices().
		Voice: &texttospeechpb.VoiceSelectionParams{
			LanguageCode: "en-US",
			SsmlGender:   texttospeechpb.SsmlVoiceGender_FEMALE,
		},
		AudioConfig: &texttospeechpb.AudioConfig{
			AudioEncoding: texttospeechpb.AudioEncoding_MP3,
		},
	}

	resp, err := client.SynthesizeSpeech(ctx, &req)
	if err != nil {
		return err
	}

	err = os.WriteFile(outputFile, resp.AudioContent, 0644)
	if err != nil {
		return err
	}
	fmt.Fprintf(w, "Audio content written to file: %v\n", outputFile)
	return nil
}

Java

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Java API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

/**
 * Demonstrates using the Text to Speech client to synthesize text or ssml.
 *
 * <p>Note: ssml must be well-formed according to: (https://www.w3.org/TR/speech-synthesis/
 * Example: <speak>Hello there.</speak>
 *
 * @param ssml the ssml document to be synthesized. (e.g., "<?xml...")
 * @throws Exception on TextToSpeechClient Errors.
 */
public static ByteString synthesizeSsml(String ssml) throws Exception {
  // Instantiates a client
  try (TextToSpeechClient textToSpeechClient = TextToSpeechClient.create()) {
    // Set the ssml input to be synthesized
    SynthesisInput input = SynthesisInput.newBuilder().setSsml(ssml).build();

    // Build the voice request
    VoiceSelectionParams voice =
        VoiceSelectionParams.newBuilder()
            .setLanguageCode("en-US") // languageCode = "en_us"
            .setSsmlGender(SsmlVoiceGender.FEMALE) // ssmlVoiceGender = SsmlVoiceGender.FEMALE
            .build();

    // Select the type of audio file you want returned
    AudioConfig audioConfig =
        AudioConfig.newBuilder()
            .setAudioEncoding(AudioEncoding.MP3) // MP3 audio.
            .build();

    // Perform the text-to-speech request
    SynthesizeSpeechResponse response =
        textToSpeechClient.synthesizeSpeech(input, voice, audioConfig);

    // Get the audio contents from the response
    ByteString audioContents = response.getAudioContent();

    // Write the response to the output file.
    try (OutputStream out = new FileOutputStream("output.mp3")) {
      out.write(audioContents.toByteArray());
      System.out.println("Audio content written to file \"output.mp3\"");
      return audioContents;
    }
  }
}

Node.js

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Node.js API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

const textToSpeech = require('@google-cloud/text-to-speech');
const fs = require('fs');
const util = require('util');

const client = new textToSpeech.TextToSpeechClient();

/**
 * TODO(developer): Uncomment the following lines before running the sample.
 */
// const ssml = '<speak>Hello there.</speak>';
// const outputFile = 'Local path to save audio file to, e.g. output.mp3';

const request = {
  input: {ssml: ssml},
  voice: {languageCode: 'en-US', ssmlGender: 'FEMALE'},
  audioConfig: {audioEncoding: 'MP3'},
};

const [response] = await client.synthesizeSpeech(request);
const writeFile = util.promisify(fs.writeFile);
await writeFile(outputFile, response.audioContent, 'binary');
console.log(`Audio content written to file: ${outputFile}`);

Python

如要瞭解如何安裝及使用 Text-to-Speech 的用戶端程式庫，請參閱「Text-to-Speech 用戶端程式庫」。詳情請參閱 Text-to-Speech Python API 參考文件。

如要進行 Text-to-Speech 驗證，請設定應用程式預設憑證。詳情請參閱「為本機開發環境設定驗證機制」。

def synthesize_ssml():
    """Synthesizes speech from the input string of ssml.

    Note: ssml must be well-formed according to:
        https://www.w3.org/TR/speech-synthesis/

    """
    from google.cloud import texttospeech

    ssml = "<speak>Hello there.</speak>"
    client = texttospeech.TextToSpeechClient()

    input_text = texttospeech.SynthesisInput(ssml=ssml)

    # Note: the voice can also be specified by name.
    # Names of voices can be retrieved with client.list_voices().
    voice = texttospeech.VoiceSelectionParams(
        language_code="en-US",
        name="en-US-Standard-C",
        ssml_gender=texttospeech.SsmlVoiceGender.FEMALE,
    )

    audio_config = texttospeech.AudioConfig(
        audio_encoding=texttospeech.AudioEncoding.MP3
    )

    response = client.synthesize_speech(
        input=input_text, voice=voice, audio_config=audio_config
    )

    # The response's audio_content is binary.
    with open("output.mp3", "wb") as out:
        out.write(response.audio_content)
        print('Audio content written to file "output.mp3"')

其他語言

C#：請按照用戶端程式庫頁面的 C# 設定操作說明完成相關步驟，然後參閱 .NET 適用的 Text-to-Speech 參考文件。

PHP：請按照用戶端程式庫頁面的 PHP 設定操作說明完成相關步驟，然後參閱 PHP 適用的 Text-to-Speech 參考文件。

Ruby：請按照用戶端程式庫頁面的 Ruby 設定操作說明完成相關步驟，然後參閱 Ruby 適用的 Text-to-Speech 參考文件。

歡迎試用

如果您不曾使用過 Google Cloud，歡迎建立帳戶，親自體驗 Text-to-Speech 的實際成效。新客戶還能獲得價值 $300 美元的免費抵免額，用於執行、測試及部署工作負載。

免費試用 Text-to-Speech

建立語音音訊檔案 透過集合功能整理內容 你可以依據偏好儲存及分類內容。

將文字轉換為合成語音音訊

通訊協定

Go

Java

Node.js

Python

其他語言

將 SSML 轉換為合成語音音訊

通訊協定

Go

Java

Node.js

Python

其他語言

歡迎試用

建立語音音訊檔案