Referensi API - Qwen-ASR-Realtime Java SDK

import com.alibaba.dashscope.audio.omni.*;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.google.gson.JsonObject;
import org.slf4j.Logger;
import org.slf4j.LoggerFactory;

import javax.sound.sampled.LineUnavailableException;
import java.io.File;
import java.io.FileInputStream;
import java.util.Base64;
import java.util.Collections;
import java.util.concurrent.CountDownLatch;
import java.util.concurrent.atomic.AtomicReference;

public class Qwen3AsrRealtimeUsage {
    private static final Logger log = LoggerFactory.getLogger(Qwen3AsrRealtimeUsage.class);
    private static final int AUDIO_CHUNK_SIZE = 1024; // Ukuran chunk audio dalam byte
    private static final int SLEEP_INTERVAL_MS = 30;  // Interval tidur dalam milidetik

    public static void main(String[] args) throws InterruptedException, LineUnavailableException {
        CountDownLatch finishLatch = new CountDownLatch(1);

        OmniRealtimeParam param = OmniRealtimeParam.builder()
                .model("qwen3-asr-flash-realtime")
                // Berikut adalah konfigurasi untuk wilayah Singapura. Saat memanggil, ganti "{WorkspaceId}" dengan ID ruang kerja Anda yang sebenarnya. Konfigurasi berbeda tiap wilayah.
                .url("wss://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api-ws/v1/realtime")
                // Kunci API berbeda antara wilayah Singapura dan Beijing. Dapatkan Kunci API Anda: https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                // Jika Anda belum mengonfigurasi variabel lingkungan, ganti baris berikut dengan Kunci API Alibaba Cloud Model Studio Anda: .apikey("sk-xxx")
                .apikey(System.getenv("DASHSCOPE_API_KEY"))
                .build();

        OmniRealtimeConversation conversation = null;
        final AtomicReference<OmniRealtimeConversation> conversationRef = new AtomicReference<>(null);
        conversation = new OmniRealtimeConversation(param, new OmniRealtimeCallback() {
            @Override
            public void onOpen() {
                System.out.println("connection opened");
            }
            @Override
            public void onEvent(JsonObject message) {
                String type = message.get("type").getAsString();
                switch(type) {
                    case "session.created":
                        System.out.println("start session: " + message.get("session").getAsJsonObject().get("id").getAsString());
                        break;
                    case "conversation.item.input_audio_transcription.completed":
                        System.out.println("transcription: " + message.get("transcript").getAsString());
                        finishLatch.countDown();
                        break;
                    case "input_audio_buffer.speech_started":
                        System.out.println("======VAD Speech Start======");
                        break;
                    case "input_audio_buffer.speech_stopped":
                        System.out.println("======VAD Speech Stop======");
                        break;
                    case "conversation.item.input_audio_transcription.text":
                        System.out.println("transcription: " + message.get("text").getAsString() + message.get("stash").getAsString());
                        break;
                    default:
                        break;
                }
            }
            @Override
            public void onClose(int code, String reason) {
                System.out.println("connection closed code: " + code + ", reason: " + reason);
            }
        });
        conversationRef.set(conversation);
        try {
            conversation.connect();
        } catch (NoApiKeyException e) {
            throw new RuntimeException(e);
        }

        OmniRealtimeTranscriptionParam transcriptionParam = new OmniRealtimeTranscriptionParam();
        transcriptionParam.setLanguage("zh");
        transcriptionParam.setInputAudioFormat("pcm");
        transcriptionParam.setInputSampleRate(16000);

        OmniRealtimeConfig config = OmniRealtimeConfig.builder()
                .modalities(Collections.singletonList(OmniRealtimeModality.TEXT))
                .transcriptionConfig(transcriptionParam)
                .build();
        conversation.updateSession(config);

        String filePath = "your_audio_file.pcm";
        File audioFile = new File(filePath);
        if (!audioFile.exists()) {
            log.error("Audio file not found: {}", filePath);
            return;
        }

        try (FileInputStream audioInputStream = new FileInputStream(audioFile)) {
            byte[] audioBuffer = new byte[AUDIO_CHUNK_SIZE];
            int bytesRead;
            int totalBytesRead = 0;

            log.info("Starting to send audio data from: {}", filePath);

            // Baca dan kirim data audio per chunk
            while ((bytesRead = audioInputStream.read(audioBuffer)) != -1) {
                totalBytesRead += bytesRead;
                String audioB64 = Base64.getEncoder().encodeToString(audioBuffer);
                // Kirim chunk audio ke percakapan
                conversation.appendAudio(audioB64);

                // Tambahkan jeda kecil untuk mensimulasikan streaming audio real-time
                Thread.sleep(SLEEP_INTERVAL_MS);
            }

            log.info("Finished sending audio data. Total bytes sent: {}", totalBytesRead);

        } catch (Exception e) {
            log.error("Error sending audio from file: {}", filePath, e);
        }

        //kirim session.finish dan tunggu selesai dan tutup
        conversation.endSession();
        log.info("task finished");

        System.exit(0);
    }
}
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";