Alibaba Cloud Model Studio:SDK de Java de Qwen-LiveTranslate - Referencia de API

OmniRealtimeParam param = OmniRealtimeParam.builder()
        .model("qwen3.5-livetranslate-flash-realtime")
        // The following is the Singapore region URL. Replace {WorkspaceId} with your actual workspace ID. URLs vary by region.
        .url("wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime")
        // API keys vary by region. To obtain an API key, see https://www.alibabacloud.com/help/model-studio/get-api-key
        // If an environment variable is not configured, replace the next line with your Model Studio API key: .apikey("sk-xxx")
        .apikey(System.getenv("DASHSCOPE_API_KEY"))
        .build();

// Set custom translation phrases
Map<String, Object> phrases = new HashMap<>();
phrases.put("Inteligencia Artificial", "Artificial Intelligence");
phrases.put("Aprendizaje Automático", "Machine Learning");

OmniRealtimeConfig config = OmniRealtimeConfig.builder()
        .modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
        .voice("Cherry")
        .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);

// Set translation phrases
Map<String, Object> phrases = new HashMap<>();
phrases.put("Inteligencia Artificial", "Artificial Intelligence");  // Source language word: Target language translation
phrases.put("Aprendizaje Automático", "Machine Learning");

OmniRealtimeTranslationParam translationParam = OmniRealtimeTranslationParam.builder()
        .language("en")  // Target language code
        .corpus(OmniRealtimeTranslationParam.Corpus.builder()
                .phrases(phrases)
                .build())
        .build();

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;

/**
 * Example of using a microphone with the real-time audio and video translation model.
 */
public class Main {
    private static final int INPUT_CHUNK_SIZE = 3200;   // 100 ms of 16 kHz, 16-bit, mono audio
    private static final int OUTPUT_CHUNK_SIZE = 4800;  // 100 ms of 24 kHz, 16-bit, mono audio
    private static final AtomicBoolean running = new AtomicBoolean(true);
    private static SourceDataLine speaker;  // Speaker

    public static void main(String[] args) throws InterruptedException {
        String apiKey = System.getenv("DASHSCOPE_API_KEY");
        if (apiKey == null || apiKey.isEmpty()) {
            System.err.println("Set the DASHSCOPE_API_KEY environment variable.");
            System.exit(1);
        }

        // Create connection parameters.
        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();

        // Create a callback handler.
        OmniRealtimeCallback callback = new OmniRealtimeCallback() {
            @Override
            public void onOpen() {
                System.out.println("[Connection established]");
            }

            @Override
            public void onEvent(JsonObject message) {
                String type = message.get("type").getAsString();
                switch (type) {
                    case "input_audio_buffer.speech_started":
                        System.out.println("====== Speech input detected ======");
                        break;
                    case "input_audio_buffer.speech_stopped":
                        System.out.println("====== Speech input ended ======");
                        break;
                    case "conversation.item.input_audio_transcription.completed":
                        String originalText = message.get("transcript").getAsString();
                        System.out.println("[Original text] " + originalText);
                        break;
                    case "response.audio_transcript.done":
                        String translatedText = message.get("transcript").getAsString();
                        System.out.println("[Translation result] " + translatedText);
                        break;
                    case "response.audio.delta":
                        // Decode and play the translated audio.
                        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("[Error] " + error.get("message").getAsString());
                        break;
                }
            }

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

        // Create a session.
        OmniRealtimeConversation conversation = new OmniRealtimeConversation(param, callback);

        try {
            // Initialize the speaker (for playing the translated speech).
            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();

            // Initialize the microphone (for capturing speech input).
            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("Microphone is not available.");
                System.exit(1);
            }
            TargetDataLine microphone = (TargetDataLine) AudioSystem.getLine(micInfo);
            microphone.open(micFormat);
            microphone.start();

            // Connect to the server.
            conversation.connect();

            // Configure translation parameters.
            Map<String, Object> phrases = new HashMap<>();
            phrases.put("Inteligencia Artificial", "Artificial Intelligence");
            phrases.put("Aprendizaje Automático", "Machine Learning");

            OmniRealtimeConfig config = OmniRealtimeConfig.builder()
                    .modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
                    .voice("Cherry")
                    .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);

            // Register a shutdown hook.
            Runtime.getRuntime().addShutdownHook(new Thread(() -> {
                System.out.println("\n[Exiting...]");
                running.set(false);
                microphone.stop();
                microphone.close();
                speaker.stop();
                speaker.close();
                try {
                    conversation.endSession();
                } catch (InterruptedException e) {
                    Thread.currentThread().interrupt();
                }
                conversation.close(1000, "User stopped");
            }));

            System.out.println("[Starting real-time translation] Speak into the microphone. Press Ctrl+C to exit.");

            // Continuously capture and send microphone audio.
            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 error: " + e.getMessage());
        } catch (Exception e) {
            System.err.println("An exception occurred: " + e.getMessage());
            e.printStackTrace();
        }
    }
}