Alibaba Cloud Model Studio:Speech synthesis (Qwen-TTS)

Python

The SpeechSynthesizer interface in the DashScope Python SDK has been consolidated into the MultiModalConversation interface. To use the new interface, simply replace the name. All other parameters are fully compatible.

# The DashScope SDK version must be 1.24.5 or later.
import os
import dashscope

# The following URL is for the Singapore region. If you use a model in the 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 = "Let me recommend a T-shirt. It is absolutely gorgeous. The color is very flattering, and it is a perfect piece for any outfit. You cannot go wrong with this one. It is really beautiful and flattering for all body types. It looks great on everyone. I highly recommend this T-shirt."
# Usage of the SpeechSynthesizer interface: dashscope.audio.qwen_tts.SpeechSynthesizer.call(...)
response = dashscope.MultiModalConversation.call(
    model="qwen3-tts-flash",
    # The API keys for the Singapore and Beijing regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with api_key="sk-xxx" using your Model Studio API key.
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    text=text,
    voice="Cherry",
    language_type="Chinese"
    stream=True
)
for chunk in response:
    print(chunk)

Java

// The DashScope SDK version must be 2.19.0 or later.
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.utils.JsonUtils;
import io.reactivex.Flowable;
import com.alibaba.dashscope.utils.Constants;

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()
                .model(MODEL)
                // The API keys for the Singapore and Beijing regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured the environment variable, replace the following line with .apiKey("sk-xxx") using your Model Studio API key.
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .text("Today is a wonderful day to build something people love!")
                .voice(AudioParameters.Voice.CHERRY)
                .languageType("English")
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.blockingForEach(r -> {System.out.println(JsonUtils.toJson(r));
        });
    }
    public static void main(String[] args) {
        // The following URL is for the Singapore region. If you use a model in the 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);
    }
}

curl

# ======= Important notes =======
# The following URL is for the Singapore region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# The API keys for the Singapore and Beijing regions are different. To obtain an API key, visit: https://www.alibabacloud.com/help/en/model-studio/get-api-key
# If you have not configured the environment variable, replace $DASHSCOPE_API_KEY with your Model Studio API key, such as sk-xxx.
# === 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": "Let me recommend a T-shirt. It is absolutely gorgeous. The color is very flattering, and it is a perfect piece for any outfit. You cannot go wrong with this one. It is really beautiful and flattering for all body types. It looks great on everyone. I highly recommend this T-shirt.",
        "voice": "Cherry",
        "language_type": "Chinese"
    }
}'