即時音視頻翻譯（Qwen-LiveTranslate）Java SDK-API參考

import com.alibaba.dashscope.audio.omni.*;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.google.gson.JsonObject;

import javax.sound.sampled.*;
import java.util.*;
import java.util.concurrent.atomic.AtomicBoolean;

/**
 * 即時音視頻翻譯模型麥克風樣本
 */
public class Main {
    private static final int INPUT_CHUNK_SIZE = 3200;   // 100ms 的 16kHz 16bit 單聲道音頻
    private static final int OUTPUT_CHUNK_SIZE = 4800;  // 100ms 的 24kHz 16bit 單聲道音頻
    private static final AtomicBoolean running = new AtomicBoolean(true);
    private static SourceDataLine speaker;  // 擴音器

    public static void main(String[] args) throws InterruptedException {
        String apiKey = System.getenv("DASHSCOPE_API_KEY");
        if (apiKey == null || apiKey.isEmpty()) {
            System.err.println("請設定環境變數 DASHSCOPE_API_KEY");
            System.exit(1);
        }

        // 建立串連參數
        OmniRealtimeParam param = OmniRealtimeParam.builder()
                .model("qwen3.5-livetranslate-flash-realtime")
                .url("wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime")
                .apikey(apiKey)
                .build();

        // 建立回調處理
        OmniRealtimeCallback callback = new OmniRealtimeCallback() {
            @Override
            public void onOpen() {
                System.out.println("[串連已建立]");
            }

            @Override
            public void onEvent(JsonObject message) {
                String type = message.get("type").getAsString();
                switch (type) {
                    case "input_audio_buffer.speech_started":
                        System.out.println("====== 檢測到語音輸入 ======");
                        break;
                    case "input_audio_buffer.speech_stopped":
                        System.out.println("====== 語音輸入結束 ======");
                        break;
                    case "conversation.item.input_audio_transcription.completed":
                        String originalText = message.get("transcript").getAsString();
                        System.out.println("[原文] " + originalText);
                        break;
                    case "response.audio_transcript.done":
                        String translatedText = message.get("transcript").getAsString();
                        System.out.println("[翻譯結果] " + translatedText);
                        break;
                    case "response.audio.delta":
                        // 解碼並播放翻譯後的音頻
                        String audioB64 = message.get("delta").getAsString();
                        byte[] audioBytes = Base64.getDecoder().decode(audioB64);
                        if (speaker != null) {
                            speaker.write(audioBytes, 0, audioBytes.length);
                        }
                        break;
                    case "error":
                        JsonObject error = message.get("error").getAsJsonObject();
                        System.err.println("[錯誤] " + error.get("message").getAsString());
                        break;
                }
            }

            @Override
            public void onClose(int code, String reason) {
                System.out.println("[串連已關閉] code: " + code + ", reason: " + reason);
            }
        };

        // 建立會話
        OmniRealtimeConversation conversation = new OmniRealtimeConversation(param, callback);

        try {
            // 初始化擴音器（用於播放翻譯後的語音）
            AudioFormat speakerFormat = new AudioFormat(24000, 16, 1, true, false);
            DataLine.Info speakerInfo = new DataLine.Info(SourceDataLine.class, speakerFormat);
            speaker = (SourceDataLine) AudioSystem.getLine(speakerInfo);
            speaker.open(speakerFormat, OUTPUT_CHUNK_SIZE * 4);
            speaker.start();

            // 初始化麥克風（用於採集語音輸入）
            AudioFormat micFormat = new AudioFormat(16000, 16, 1, true, false);
            DataLine.Info micInfo = new DataLine.Info(TargetDataLine.class, micFormat);
            if (!AudioSystem.isLineSupported(micInfo)) {
                System.err.println("麥克風不可用");
                System.exit(1);
            }
            TargetDataLine microphone = (TargetDataLine) AudioSystem.getLine(micInfo);
            microphone.open(micFormat);
            microphone.start();

            // 串連服務端
            conversation.connect();

            // 配置翻譯參數
            Map<String, Object> phrases = new HashMap<>();
            phrases.put("人工智慧", "Artificial Intelligence");
            phrases.put("機器學習", "Machine Learning");

            OmniRealtimeConfig config = OmniRealtimeConfig.builder()
                    .modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
                    .voice("Tina")
                    .inputAudioFormat(OmniRealtimeAudioFormat.PCM_16000HZ_MONO_16BIT)
                    .outputAudioFormat(OmniRealtimeAudioFormat.PCM_24000HZ_MONO_16BIT)
                    .InputAudioTranscription("qwen3-asr-flash-realtime")
                    .translationConfig(OmniRealtimeTranslationParam.builder()
                            .language("en")
                            .corpus(OmniRealtimeTranslationParam.Corpus.builder()
                                    .phrases(phrases)
                                    .build())
                            .build())
                    .build();

            conversation.updateSession(config);

            // 註冊退出訊號處理
            Runtime.getRuntime().addShutdownHook(new Thread(() -> {
                System.out.println("\n[正在退出...]");
                running.set(false);
                microphone.stop();
                microphone.close();
                speaker.stop();
                speaker.close();
                try {
                    conversation.endSession();
                } catch (InterruptedException e) {
                    Thread.currentThread().interrupt();
                }
                conversation.close(1000, "使用者停止");
            }));

            System.out.println("[開始即時翻譯] 請對著麥克風說話，按 Ctrl+C 退出");

            // 持續採集麥克風音頻並發送
            byte[] buffer = new byte[INPUT_CHUNK_SIZE];
            while (running.get()) {
                int bytesRead = microphone.read(buffer, 0, buffer.length);
                if (bytesRead > 0) {
                    conversation.appendAudio(Base64.getEncoder().encodeToString(buffer));
                }
            }

        } catch (NoApiKeyException e) {
            System.err.println("API Key 錯誤: " + e.getMessage());
        } catch (Exception e) {
            System.err.println("發生異常: " + e.getMessage());
            e.printStackTrace();
        }
    }
}