Qwen-Audio-ASR-Streaming Java SDK provides interfaces for synchronous and streaming speech recognition

import com.alibaba.dashscope.audio.asr.recognition.Recognition;
import com.alibaba.dashscope.audio.asr.recognition.RecognitionParam;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;
import io.reactivex.BackpressureStrategy;
import io.reactivex.Flowable;

import javax.sound.sampled.AudioFormat;
import javax.sound.sampled.AudioSystem;
import javax.sound.sampled.TargetDataLine;
import java.nio.ByteBuffer;

public class Main {
    public static void main(String[] args) throws NoApiKeyException {
        // Singapore (ap-southeast-1). For another region, replace ap-southeast-1 in the URL.
        // API keys are region-specific. See https://docs.qwencloud.com/developer-guides/getting-started/regions
        Constants.baseWebsocketApiUrl = "wss://ap-southeast-1.maas.qwencloudapi.com/api-ws/v1/inference";
        // Create a Flowable<ByteBuffer>
        Flowable<ByteBuffer> audioSource =
                Flowable.create(
                        emitter -> {
                            new Thread(
                                    () -> {
                                        try {
                                            // Create the audio format
                                            AudioFormat audioFormat = new AudioFormat(16000, 16, 1, true, false);
                                            // Match the default recording device based on the format
                                            TargetDataLine targetDataLine =
                                                    AudioSystem.getTargetDataLine(audioFormat);
                                            targetDataLine.open(audioFormat);
                                            // Start recording
                                            targetDataLine.start();
                                            ByteBuffer buffer = ByteBuffer.allocate(1024);
                                            long start = System.currentTimeMillis();
                                            // Record for 50s and perform real-time transcription
                                            while (System.currentTimeMillis() - start < 50000) {
                                                int read = targetDataLine.read(buffer.array(), 0, buffer.capacity());
                                                if (read > 0) {
                                                    buffer.limit(read);
                                                    // Send the recorded audio data to the streaming recognition service
                                                    emitter.onNext(buffer);
                                                    buffer = ByteBuffer.allocate(1024);
                                                    // The recording rate is limited; sleep for a short while to prevent excessive CPU usage
                                                    Thread.sleep(20);
                                                }
                                            }
                                            // Notify that transcription has ended
                                            emitter.onComplete();
                                        } catch (Exception e) {
                                            emitter.onError(e);
                                        }
                                    })
                                    .start();
                        },
                        BackpressureStrategy.BUFFER);

        // Create the Recognizer
        Recognition recognizer = new Recognition();
        // Create RecognitionParam and pass the Flowable<ByteBuffer> created above into the audioFrames parameter
        RecognitionParam param = RecognitionParam.builder()
                .model("qwen-audio-3.0-asr-flash-streaming")
                // If you have not configured the environment variable, replace the following line with your QwenCloud API Key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .format("pcm")
                .sampleRate(16000)
                .build();

        // Streaming call interface
        recognizer
                .streamCall(param, audioSource)
                .blockingForEach(
                        result -> {
                            // Subscribe to the output result
                            if (result.isSentenceEnd()) {
                                System.out.println("Final Result: " + result.getSentence().getText());
                            } else {
                                System.out.println("Intermediate Result: " + result.getSentence().getText());
                            }
                        });
        // Close the WebSocket connection after the task is complete
        recognizer.getDuplexApi().close(1000, "bye");
        System.out.println(
                "[Metric] requestId: "
                        + recognizer.getLastRequestId()
                        + ", first package delay ms: "
                        + recognizer.getFirstPackageDelay()
                        + ", last package delay ms: "
                        + recognizer.getLastPackageDelay());
        System.exit(0);
    }
}