Qwen-Audio-TTS non-real-time speech synthesis Java SDK reference

Non-streaming

Non-streaming calls wait for synthesis to complete, then return the full result. Two return types are available:

• callAndReturnAudio(): Returns audio binary data (ByteBuffer). Use this to save or process the audio directly.
• call(): Returns an audio URL. Use this to download the audio from a URL.

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 {
        // The following is the configuration for the China (Beijing) region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.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-3.0-tts-flash")  // When switching models, also switch to a compatible voice version
                .text("Behind my house is a big garden.")
                .voice("longanhuan_v3.6")
                .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-3.0-tts-flash")  // When switching models, also switch to a compatible voice version
                .text("Behind my house is a big garden.")
                .voice("longanhuan_v3.6")
                .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();
    }
}

Streaming

Streaming calls return audio data in chunks through a callback as synthesis progresses. Use this mode for real-time playback where low first-packet latency matters.

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.common.ResultCallback;
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.util.concurrent.CountDownLatch;

public class QwenAudioTtsStreamExample {
    static {
        // The following is the configuration for the China (Beijing) region. Replace "{WorkspaceId}" with your actual workspace ID. The configuration varies by region.
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
    }

    public static void streamCallWithCallback() {
        HttpSpeechSynthesizer synthesizer = new HttpSpeechSynthesizer();

        HttpSpeechSynthesisParam param =
                HttpSpeechSynthesisParam.builder()
                        .model("qwen-audio-3.0-tts-flash")  // When switching models, also switch to a compatible voice version
                        .text("The weather is great today, perfect for going out.")
                        .voice("longanhuan_v3.6")
                        .format("wav")
                        .sampleRate(24000)
                        // If the environment variable is not set, replace with: apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .build();

        CountDownLatch latch = new CountDownLatch(1);

        // Create the output file stream
        try (FileOutputStream fos = new FileOutputStream("output.wav")) {

            synthesizer.streamCall(param,
                    new ResultCallback<HttpSpeechSynthesisResult>() {
                        private int chunkCount = 0;

                        @Override
                        public void onEvent(HttpSpeechSynthesisResult result) {
                            chunkCount++;
                            if (result.hasAudioData()) {
                                System.out.println("Received chunk #" + chunkCount
                                        + ", size: " + result.getAudioDataSize() + " bytes");
                                try {
                                    fos.write(result.getAudioData());
                                } catch (IOException e) {
                                    System.err.println("Failed to write audio data: " + e.getMessage());
                                }
                            }
                            if (result.getRequestId() != null) {
                                System.out.println("Request ID: " + result.getRequestId());
                            }
                        }

                        @Override
                        public void onComplete() {
                            System.out.println("Synthesis completed, total chunks: " + chunkCount);
                            System.out.println("Audio saved to output.wav");
                            latch.countDown();
                        }

                        @Override
                        public void onError(Exception e) {
                            System.err.println("Error during synthesis: " + e.getMessage());
                            latch.countDown();
                        }
                    });

            latch.await();

        } catch (ApiException | NoApiKeyException | InputRequiredException | InterruptedException e) {
            System.err.println("Failed: " + e.getMessage());
        } catch (IOException e) {
            System.err.println("Failed to create output file: " + e.getMessage());
        }
    }

    public static void main(String[] args) {
        streamCallWithCallback();
        System.exit(0);
    }
}