<!-- Add Google Cloud Speech-to-Text dependency -->
<dependency>
    <groupId>com.google.cloud</groupId>
    <artifactId>google-cloud-speech</artifactId>
    <version>YOUR_VERSION</version>
</dependency>

// 導(dǎo)入必要的庫(kù)
import com.google.cloud.speech.v1.RecognitionAudio;
import com.google.cloud.speech.v1.RecognitionConfig;
import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding;
import com.google.cloud.speech.v1.SpeechClient;
import com.google.cloud.speech.v1.SpeechRecognitionAlternative;
import com.google.cloud.speech.v1.SpeechRecognitionResult;
import com.google.cloud.speech.v1.SyncRecognizeResponse;

import java.io.FileInputStream;
import java.nio.file.Files;
import java.nio.file.Paths;

public class AudioToText {

    public static void main(String[] args) throws Exception {
        // 初始化SpeechClient（需要API密鑰或服務(wù)賬戶(hù)憑據(jù)）
        try (SpeechClient speechClient = SpeechClient.create()) {

            // 讀取音頻文件（這里假設(shè)是WAV格式）
            byte[] audioBytes = Files.readAllBytes(Paths.get("path_to_your_audio_file.wav"));

            // 設(shè)置識(shí)別配置
            RecognitionConfig config = RecognitionConfig.newBuilder()
                .setEncoding(AudioEncoding.LINEAR16) // 設(shè)置音頻編碼格式
                .setSampleRateHertz(16000) // 設(shè)置音頻采樣率（根據(jù)文件實(shí)際情況）
                .setLanguageCode("en-US") // 設(shè)置識(shí)別語(yǔ)言
                .build();

            // 設(shè)置音頻數(shù)據(jù)
            RecognitionAudio audio = RecognitionAudio.newBuilder().setContent(audioBytes).build();

            // 調(diào)用同步識(shí)別方法
            SyncRecognizeResponse response = speechClient.syncRecognize(config, audio);

            // 處理識(shí)別結(jié)果
            for (SpeechRecognitionResult result : response.getResultsList()) {
                // 每個(gè)結(jié)果可能包含多個(gè)替代方案（即不同的識(shí)別可能）
                for (SpeechRecognitionAlternative alternative : result.getAlternativesList()) {
                    System.out.printf("Transcription: %s%n", alternative.getTranscript());
                }
            }
        }
    }
}

<dependencies>
    <!-- ... 其他依賴(lài) ... -->
    <dependency>
        <groupId>com.google.cloud</groupId>
        <artifactId>google-cloud-speech</artifactId>
        <version>YOUR_VERSION</version> <!-- 請(qǐng)?zhí)鎿Q為最新版本 -->
    </dependency>
    <!-- ... 其他依賴(lài) ... -->
</dependencies>

import com.google.api.gax.rpc.ApiException;
import com.google.cloud.speech.v1.RecognitionAudio;
import com.google.cloud.speech.v1.RecognitionConfig;
import com.google.cloud.speech.v1.RecognitionConfig.AudioEncoding;
import com.google.cloud.speech.v1.SpeechClient;
import com.google.cloud.speech.v1.SpeechRecognitionAlternative;
import com.google.cloud.speech.v1.SpeechRecognitionResult;
import com.google.cloud.speech.v1.SyncRecognizeResponse;
import com.google.auth.oauth2.GoogleCredentials;
import com.google.auth.oauth2.ServiceAccountCredentials;

import java.io.FileInputStream;
import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.List;

public class AudioToTextWithErrorHandling {

    // 從Google Cloud平臺(tái)下載的服務(wù)賬戶(hù)憑據(jù)JSON文件的路徑
    private static final String CREDENTIALS_FILE_PATH = "/path/to/your/service-account.json";

    // 音頻文件路徑
    private static final String AUDIO_FILE_PATH = "/path/to/your/audio_file.wav";

    public static void main(String[] args) {
        try {
            // 初始化SpeechClient
            try (SpeechClient speechClient = createSpeechClient()) {

                // 讀取音頻文件
                byte[] audioBytes = Files.readAllBytes(Paths.get(AUDIO_FILE_PATH));

                // 設(shè)置識(shí)別配置
                RecognitionConfig config = RecognitionConfig.newBuilder()
                        .setEncoding(AudioEncoding.LINEAR16) // 設(shè)置音頻編碼格式
                        .setSampleRateHertz(16000) // 設(shè)置音頻采樣率（根據(jù)文件實(shí)際情況）
                        .setLanguageCode("en-US") // 設(shè)置識(shí)別語(yǔ)言
                        .build();

                // 設(shè)置音頻數(shù)據(jù)
                RecognitionAudio audio = RecognitionAudio.newBuilder().setContent(audioBytes).build();

                // 調(diào)用同步識(shí)別方法
                SyncRecognizeResponse response = speechClient.syncRecognize(config, audio);

                // 處理識(shí)別結(jié)果
                List<SpeechRecognitionResult> results = response.getResultsList();
                for (SpeechRecognitionResult result : results) {
                    // 每個(gè)結(jié)果可能包含多個(gè)替代方案（即不同的識(shí)別可能）
                    SpeechRecognitionAlternative alternative = result.getAlternativesList().get(0);
                    System.out.printf("Transcription: %s%n", alternative.getTranscript());
                }

            } catch (ApiException e) {
                // 處理API異常
                System.err.println("API Exception: " + e.getMessage());
                e.printStackTrace();
            } catch (Exception e) {
                // 處理其他異常
                System.err.println("General Exception: " + e.getMessage());
                e.printStackTrace();
            }

        } catch (IOException e) {
            // 處理文件讀取異常
            System.err.println("Error reading audio file: " + e.getMessage());
            e.printStackTrace();
        }
    }

    // 創(chuàng)建一個(gè)帶有服務(wù)賬戶(hù)憑據(jù)的SpeechClient
    private static SpeechClient createSpeechClient() throws IOException {
        // 使用Google服務(wù)賬戶(hù)憑據(jù)
        try (FileInputStream serviceAccountStream =
                     new FileInputStream(CREDENTIALS_FILE_PATH)) {

            // 加載服務(wù)賬戶(hù)憑據(jù)
            GoogleCredentials credentials = ServiceAccountCredentials.fromStream(serviceAccountStream);

            // 構(gòu)建SpeechClient
            SpeechClient speechClient = SpeechClient.create(SpeechClient.createSettings().withCredentials(credentials));
            return speechClient;
        }
    }
}