Qwen-Audio-TTS HTTP Java SDK

import com.alibaba.dashscope.audio.http_tts.AudioInfo;
import com.alibaba.dashscope.audio.http_tts.HttpSpeechSynthesisParam;
import com.alibaba.dashscope.audio.http_tts.HttpSpeechSynthesisResult;
import com.alibaba.dashscope.audio.http_tts.HttpSpeechSynthesizer;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.InputRequiredException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.utils.Constants;

import java.io.FileOutputStream;
import java.io.IOException;
import java.nio.ByteBuffer;

public class QwenAudioTtsSyncExample {
    static {
        // 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.baseHttpApiUrl = "https://ap-southeast-1.maas.qwencloudapi.com/api/v1";
    }

    /**
     * Non-streaming example 1: Returns audio data (ByteBuffer)
     * Calls callAndReturnAudio, which blocks until synthesis completes and returns the full audio data.
     */
    public static void syncCallReturnAudio() {
        HttpSpeechSynthesizer synthesizer = new HttpSpeechSynthesizer();

        HttpSpeechSynthesisParam param =
            HttpSpeechSynthesisParam.builder()
                .model("qwen-audio-3.1-tts-flash")  // When switching models, also switch to a compatible voice version
                .text("Behind my house is a big garden.")
                .voice("longanhuan_v3.1")
                .format("wav")
                .sampleRate(24000)
                // If the environment variable is not set, replace with: apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // Set additional parameters using the parameter method
                // .parameter("seed", 1234)
                // .parameter("enable_ssml", true)
                .build();

        try {
            ByteBuffer audioData = synthesizer.callAndReturnAudio(param);
            if (audioData != null && audioData.hasRemaining()) {
                byte[] bytes = new byte[audioData.remaining()];
                audioData.get(bytes);

                try (FileOutputStream fos = new FileOutputStream("sync_output.wav")) {
                    fos.write(bytes);
                    System.out.println("Audio saved to sync_output.wav, size: " + bytes.length + " bytes");
                } catch (IOException e) {
                    System.err.println("Failed to save audio: " + e.getMessage());
                }
            }
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            System.err.println("Synthesis failed: " + e.getMessage());
        }
        System.exit(0);
    }

    /**
     * Non-streaming example 2: Returns an audio URL
     * Calls call, which returns a result object containing an audio URL for downloading.
     */
    public static void syncCallReturnUrl() {
        HttpSpeechSynthesizer synthesizer = new HttpSpeechSynthesizer();

        HttpSpeechSynthesisParam param =
            HttpSpeechSynthesisParam.builder()
                .model("qwen-audio-3.1-tts-flash")  // When switching models, also switch to a compatible voice version
                .text("Behind my house is a big garden.")
                .voice("longanhuan_v3.1")
                .format("wav")
                .sampleRate(24000)
                // If the environment variable is not set, replace with: apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .build();

        try {
            HttpSpeechSynthesisResult result = synthesizer.call(param);
            System.out.println("Request ID: " + result.getRequestId());

            if (result.hasAudioUrl()) {
                AudioInfo audioInfo = result.getAudioInfo();
                System.out.println("Audio URL: " + audioInfo.getUrl());
                System.out.println("Expires At: " + audioInfo.getExpiresAt());
                System.out.println("Remaining Time: " + audioInfo.getRemainingSeconds() + " seconds");
            }
        } catch (ApiException | NoApiKeyException | InputRequiredException e) {
            System.err.println("Synthesis failed: " + e.getMessage());
        }
    }

    public static void main(String[] args) {
        // Non-streaming example 1: Returns audio data (ByteBuffer)
        // syncCallReturnAudio();
        // Non-streaming example 2: Returns an audio URL
        syncCallReturnUrl();
    }
}