Alibaba Cloud Model Studio:Qwen speech synthesis models

# DashScope SDK version 1.24.6 or later
import os
import dashscope

# This is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

text = "I want to recommend a T-shirt. It's incredibly stylish, and the color is very flattering. It's a perfect piece for any outfit. You can't go wrong with it. It's really beautiful and suits all body types, so anyone will look great wearing it. I highly recommend ordering one."
# To use the SpeechSynthesizer interface: dashscope.audio.qwen_tts.SpeechSynthesizer.call(...)
response = dashscope.MultiModalConversation.call(
    model="qwen3-tts-flash",
    # API keys for the Singapore and China (Beijing) regions are different. To get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    text=text,
    voice="Cherry",
    language_type="Chinese", # We recommend that this matches the text language to ensure correct pronunciation and natural intonation.
    stream=False
)
print(response)

// DashScope SDK version 2.21.9 or later
// Versions 2.20.7 and later support the Dylan, Jada, and Sunny voices.
import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.protocol.Protocol;
import com.alibaba.dashscope.utils.Constants;

import java.io.FileOutputStream;
import java.io.InputStream;
import java.net.URL;

public class Main {
    private static final String MODEL = "qwen3-tts-flash";
    public static void call() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and China (Beijing) regions are different. To get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model(MODEL)
                .text("Today is a wonderful day to build something people love!")
                .voice(AudioParameters.Voice.CHERRY)
                .languageType("English") // We recommend that this matches the text language to ensure correct pronunciation and natural intonation.
                .build();
        MultiModalConversationResult result = conv.call(param);
        String audioUrl = result.getOutput().getAudio().getUrl();
        System.out.print(audioUrl);

        // Download the audio file locally
        try (InputStream in = new URL(audioUrl).openStream();
             FileOutputStream out = new FileOutputStream("downloaded_audio.wav")) {
            byte[] buffer = new byte[1024];
            int bytesRead;
            while ((bytesRead = in.read(buffer)) != -1) {
                out.write(buffer, 0, bytesRead);
            }
            System.out.println("\nAudio file downloaded to local path: downloaded_audio.wav");
        } catch (Exception e) {
            System.out.println("\nError downloading audio file: " + e.getMessage());
        }
    }
    public static void main(String[] args) {
        // This is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1";
        try {
            call();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= Important =======
# This is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and China (Beijing) regions are different. To get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-d '{
    "model": "qwen3-tts-flash",
    "input": {
        "text": "I want to recommend a T-shirt. It'\''s incredibly stylish, and the color is very flattering. It'\''s a perfect piece for any outfit. You can'\''t go wrong with it. It'\''s really beautiful and suits all body types, so anyone will look great wearing it. I highly recommend ordering one.",
        "voice": "Cherry",
        "language_type": "Chinese"
    }
}'

# DashScope SDK version 1.24.6 or later
# coding=utf-8
#
# Installation instructions for pyaudio:
# APPLE Mac OS X
#   brew install portaudio
#   pip install pyaudio
# Debian/Ubuntu
#   sudo apt-get install python-pyaudio python3-pyaudio
#   or
#   pip install pyaudio
# CentOS
#   sudo yum install -y portaudio portaudio-devel && pip install pyaudio
# Microsoft Windows
#   python -m pip install pyaudio

import os
import dashscope
import pyaudio
import time
import base64
import numpy as np

# This is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

p = pyaudio.PyAudio()
# Create an audio stream
stream = p.open(format=pyaudio.paInt16,
                channels=1,
                rate=24000,
                output=True)


text = "Hello, I am Qwen"
response = dashscope.MultiModalConversation.call(
    # API keys for the Singapore and China (Beijing) regions are different. To get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured an environment variable, replace the following line with your Model Studio API key: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-tts-flash",
    text=text,
    voice="Cherry",
    language_type="Chinese", # We recommend that this matches the text language to ensure correct pronunciation and natural intonation.
    stream=True
)

for chunk in response:
    if chunk.output is not None:
      audio = chunk.output.audio
      if audio.data is not None:
          wav_bytes = base64.b64decode(audio.data)
          audio_np = np.frombuffer(wav_bytes, dtype=np.int16)
          # Play the audio data directly
          stream.write(audio_np.tobytes())
      if chunk.output.finish_reason == "stop":
          print("finish at: {} ", chunk.output.audio.expires_at)
time.sleep(0.8)
# Clean up resources
stream.stop_stream()
stream.close()
p.terminate()

// Install the latest version of the DashScope SDK
// Versions 2.20.7 and later support the Dylan, Jada, and Sunny voices.
import com.alibaba.dashscope.aigc.multimodalconversation.AudioParameters;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversation;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationParam;
import com.alibaba.dashscope.aigc.multimodalconversation.MultiModalConversationResult;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.protocol.Protocol;
import com.alibaba.dashscope.utils.Constants;
import io.reactivex.Flowable;
import javax.sound.sampled.*;
import java.util.Base64;

public class Main {
    private static final String MODEL = "qwen3-tts-flash";
    public static void streamCall() throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // API keys for the Singapore and China (Beijing) regions are different. To get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured an environment variable, replace the following line with your Model Studio API key: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model(MODEL)
                .text("Today is a wonderful day to build something people love!")
                .voice(AudioParameters.Voice.CHERRY)
                .languageType("English") // We recommend that this matches the text language to ensure correct pronunciation and natural intonation.
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(r -> {
            try {
                // 1. Get the Base64-encoded audio data
                String base64Data = r.getOutput().getAudio().getData();
                byte[] audioBytes = Base64.getDecoder().decode(base64Data);

                // 2. Configure the audio format (adjust based on the format returned by the API)
                AudioFormat format = new AudioFormat(
                        AudioFormat.Encoding.PCM_SIGNED,
                        24000, // Sample rate (must match the format returned by the API)
                        16,    // Audio bit depth
                        1,     // Number of sound channels
                        2,     // Frame size (bit depth / 8)
                        16000, // Data transfer rate
                        false  // Is compressed
                );

                // 3. Play the audio data in real time
                DataLine.Info info = new DataLine.Info(SourceDataLine.class, format);
                try (SourceDataLine line = (SourceDataLine) AudioSystem.getLine(info)) {
                    if (line != null) {
                        line.open(format);
                        line.start();
                        line.write(audioBytes, 0, audioBytes.length);
                        line.drain();
                    }
                }
            } catch (LineUnavailableException e) {
                e.printStackTrace();
            }
        });
    }
    public static void main(String[] args) {
        // This is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1";
        try {
            streamCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

# ======= Important =======
# This is the URL for the Singapore region. If you use a model in the China (Beijing) region, replace the URL with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# API keys for the Singapore and China (Beijing) regions are different. To get an API key: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X POST 'https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H 'Content-Type: application/json' \
-H 'X-DashScope-SSE: enable' \
-d '{
    "model": "qwen3-tts-flash",
    "input": {
        "text": "I want to recommend a T-shirt. It'\''s incredibly stylish, and the color is very flattering. It'\''s a perfect piece for any outfit. You can'\''t go wrong with it. It'\''s really beautiful and suits all body types, so anyone will look great wearing it. I highly recommend ordering one.",
        "voice": "Cherry",
        "language_type": "Chinese"
    }
}'