Alibaba Cloud Model Studio:Audio file recognition - Qwen

Submit a task

# ======= Important =======
# 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/audio/asr/transcription
# The API keys for the Singapore and Beijing regions are different. To obtain an API key, see 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/audio/asr/transcription' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-H "X-DashScope-Async: enable" \
-d '{
    "model": "qwen3-asr-flash-filetrans",
    "input": {
        "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
    },
    "parameters": {
        "channel_id":[
            0
        ], 
        "enable_itn": false,
        "enable_words": true
    }
}'

Get the task result

# ======= Important =======
# 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/tasks/{task_id}. Note: Replace {task_id} with the ID of the task to query.
# The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# === Delete this comment before execution ===

curl -X GET 'https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id}' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "X-DashScope-Async: enable" \
-H "Content-Type: application/json"

Complete example

import com.google.gson.Gson;
import com.google.gson.annotations.SerializedName;
import okhttp3.*;

import java.io.IOException;
import java.util.concurrent.TimeUnit;

public class Main {
    // 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/audio/asr/transcription
    private static final String API_URL_SUBMIT = "https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription";
    // 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/tasks/
    private static final String API_URL_QUERY = "https://dashscope-intl.aliyuncs.com/api/v1/tasks/";
    private static final Gson gson = new Gson();

    public static void main(String[] args) {
        // The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
        // If you have not configured environment variables, replace the following line with: String apiKey = "sk-xxx"
        String apiKey = System.getenv("DASHSCOPE_API_KEY");

        OkHttpClient client = new OkHttpClient();

        // 1. Submit the task
        /*String payloadJson = """
                {
                    "model": "qwen3-asr-flash-filetrans",
                    "input": {
                        "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                    },
                    "parameters": {
                        "channel_id": [0],
                        "enable_itn": false,
                        "language": "zh"
                    }
                }
                """;*/
        String payloadJson = """
                {
                    "model": "qwen3-asr-flash-filetrans",
                    "input": {
                        "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                    },
                    "parameters": {
                        "channel_id": [0],
                        "enable_itn": false,
                        "enable_words": true
                    }
                }
                """;

        RequestBody body = RequestBody.create(payloadJson, MediaType.get("application/json; charset=utf-8"));
        Request submitRequest = new Request.Builder()
                .url(API_URL_SUBMIT)
                .addHeader("Authorization", "Bearer " + apiKey)
                .addHeader("Content-Type", "application/json")
                .addHeader("X-DashScope-Async", "enable")
                .post(body)
                .build();

        String taskId = null;

        try (Response response = client.newCall(submitRequest).execute()) {
            if (response.isSuccessful() && response.body() != null) {
                String respBody = response.body().string();
                ApiResponse apiResp = gson.fromJson(respBody, ApiResponse.class);
                if (apiResp.output != null) {
                    taskId = apiResp.output.taskId;
                    System.out.println("Task submitted. task_id: " + taskId);
                } else {
                    System.out.println("Submission response content: " + respBody);
                    return;
                }
            } else {
                System.out.println("Task submission failed! HTTP code: " + response.code());
                if (response.body() != null) {
                    System.out.println(response.body().string());
                }
                return;
            }
        } catch (IOException e) {
            e.printStackTrace();
            return;
        }

        // 2. Poll the task status
        boolean finished = false;
        while (!finished) {
            try {
                TimeUnit.SECONDS.sleep(2);  // Wait for 2 seconds before querying again
            } catch (InterruptedException e) {
                Thread.currentThread().interrupt();
                return;
            }

            String queryUrl = API_URL_QUERY + taskId;
            Request queryRequest = new Request.Builder()
                    .url(queryUrl)
                    .addHeader("Authorization", "Bearer " + apiKey)
                    .addHeader("X-DashScope-Async", "enable")
                    .addHeader("Content-Type", "application/json")
                    .get()
                    .build();

            try (Response response = client.newCall(queryRequest).execute()) {
                if (response.body() != null) {
                    String queryResponse = response.body().string();
                    ApiResponse apiResp = gson.fromJson(queryResponse, ApiResponse.class);

                    if (apiResp.output != null && apiResp.output.taskStatus != null) {
                        String status = apiResp.output.taskStatus;
                        System.out.println("Current task status: " + status);
                        if ("SUCCEEDED".equalsIgnoreCase(status)
                                || "FAILED".equalsIgnoreCase(status)
                                || "UNKNOWN".equalsIgnoreCase(status)) {
                            finished = true;
                            System.out.println("Task completed. Final result: ");
                            System.out.println(queryResponse);
                        }
                    } else {
                        System.out.println("Query response content: " + queryResponse);
                    }
                }
            } catch (IOException e) {
                e.printStackTrace();
                return;
            }
        }
    }

    static class ApiResponse {
        @SerializedName("request_id")
        String requestId;
        Output output;
    }

    static class Output {
        @SerializedName("task_id")
        String taskId;
        @SerializedName("task_status")
        String taskStatus;
    }
}

import os
import time
import requests
import json

# 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/audio/asr/transcription
API_URL_SUBMIT = "https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription"
# 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/tasks/
API_URL_QUERY_BASE = "https://dashscope-intl.aliyuncs.com/api/v1/tasks/"


def main():
    # The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured environment variables, replace the following line with: api_key = "sk-xxx"
    api_key = os.getenv("DASHSCOPE_API_KEY")

    headers = {
        "Authorization": f"Bearer {api_key}",
        "Content-Type": "application/json",
        "X-DashScope-Async": "enable"
    }

    # 1. Submit the task
    payload = {
        "model": "qwen3-asr-flash-filetrans",
        "input": {
            "file_url": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
        },
        "parameters": {
            "channel_id": [0],
            # "language": "zh",
            "enable_itn": False,
            "enable_words": True
        }
    }

    print("Submitting ASR transcription task...")
    try:
        submit_resp = requests.post(API_URL_SUBMIT, headers=headers, data=json.dumps(payload))
    except requests.RequestException as e:
        print(f"Failed to submit task request: {e}")
        return

    if submit_resp.status_code != 200:
        print(f"Task submission failed! HTTP code: {submit_resp.status_code}")
        print(submit_resp.text)
        return

    resp_data = submit_resp.json()
    output = resp_data.get("output")
    if not output or "task_id" not in output:
        print("Abnormal submission response content:", resp_data)
        return

    task_id = output["task_id"]
    print(f"Task submitted. task_id: {task_id}")

    # 2. Poll the task status
    finished = False
    while not finished:
        time.sleep(2)  # Wait for 2 seconds before querying again

        query_url = API_URL_QUERY_BASE + task_id
        try:
            query_resp = requests.get(query_url, headers=headers)
        except requests.RequestException as e:
            print(f"Failed to query task: {e}")
            return

        if query_resp.status_code != 200:
            print(f"Task query failed! HTTP code: {query_resp.status_code}")
            print(query_resp.text)
            return

        query_data = query_resp.json()
        output = query_data.get("output")
        if output and "task_status" in output:
            status = output["task_status"]
            print(f"Current task status: {status}")

            if status.upper() in ("SUCCEEDED", "FAILED", "UNKNOWN"):
                finished = True
                print("Task completed. Final result:")
                print(json.dumps(query_data, indent=2, ensure_ascii=False))
        else:
            print("Query response content:", query_data)


if __name__ == "__main__":
    main()

Python SDK

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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {"role": "system", "content": [{"text": ""}]},  # Configure the context for customized recognition
    {"role": "user", "content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}
]

response = dashscope.MultiModalConversation.call(
    # The API keys for the Singapore/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured environment variables, replace the following line with: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        #"language": "zh", # Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        "enable_itn":False
    }
)
print(response)

Java SDK

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

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.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3")))
                .build();

        MultiModalMessage sysMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                // Configure the context for customized recognition here
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured environment variables, replace the following line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
                .model("qwen3-asr-flash")
                .message(sysMessage)
                .message(userMessage)
                .parameter("asr_options", asrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }
    public static void main(String[] args) {
        try {
            // 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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

cURL

# ======= Important =======
# The following URL is for the Singapore region. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation. 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/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# If you use a model in the US region, you must add the "us" suffix.
# === 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-asr-flash",
    "input": {
        "messages": [
            {
                "content": [
                    {
                        "text": ""
                    }
                ],
                "role": "system"
            },
            {
                "content": [
                    {
                        "audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                    }
                ],
                "role": "user"
            }
        ]
    },
    "parameters": {
        "asr_options": {
            "enable_itn": false
        }
    }
}'

Python SDK

import base64
import dashscope
import os
import pathlib

# 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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Replace with the actual path to your audio file
file_path = "welcome.mp3"
# Replace with the actual MIME type of your audio file
audio_mime_type = "audio/mpeg"

file_path_obj = pathlib.Path(file_path)
if not file_path_obj.exists():
    raise FileNotFoundError(f"Audio file not found: {file_path}")

base64_str = base64.b64encode(file_path_obj.read_bytes()).decode()
data_uri = f"data:{audio_mime_type};base64,{base64_str}"

messages = [
    {"role": "system", "content": [{"text": ""}]},  # Configure the context for customized recognition
    {"role": "user", "content": [{"audio": data_uri}]}
]
response = dashscope.MultiModalConversation.call(
    # The API keys for the Singapore/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured environment variables, replace the following line with: api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        # "language": "zh", # Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        "enable_itn":False
    }
)
print(response)

Java SDK

import java.io.IOException;
import java.nio.file.Files;
import java.nio.file.Paths;
import java.util.*;

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.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    // Replace with the actual path to your audio file
    private static final String AUDIO_FILE = "welcome.mp3";
    // Replace with the actual MIME type of your audio file
    private static final String AUDIO_MIME_TYPE = "audio/mpeg";

    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException, IOException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("audio", toDataUrl())))
                .build();

        MultiModalMessage sysMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                // Configure the context for customized recognition here
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured environment variables, replace the following line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
                .model("qwen3-asr-flash")
                .message(sysMessage)
                .message(userMessage)
                .parameter("asr_options", asrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }

    public static void main(String[] args) {
        try {
            // 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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }

    // Generate a data URI
    public static String toDataUrl() throws IOException {
        byte[] bytes = Files.readAllBytes(Paths.get(AUDIO_FILE));
        String encoded = Base64.getEncoder().encodeToString(bytes);
        return "data:" + AUDIO_MIME_TYPE + ";base64," + encoded;
    }
}

Python SDK

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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

# Replace ABSOLUTE_PATH/welcome.mp3 with the absolute path of your local audio file.
audio_file_path = "file://ABSOLUTE_PATH/welcome.mp3"

messages = [
    {"role": "system", "content": [{"text": ""}]},  # Configure the context for customized recognition
    {"role": "user", "content": [{"audio": audio_file_path}]}
]
response = dashscope.MultiModalConversation.call(
    # The API keys for the Singapore/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured environment variables, replace the following line with: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        # "language": "zh", # Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        "enable_itn":False
    }
)
print(response)

Java SDK

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

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.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;
import com.alibaba.dashscope.utils.JsonUtils;

public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        // Replace ABSOLUTE_PATH/welcome.mp3 with the absolute path of your local file.
        String localFilePath = "file://ABSOLUTE_PATH/welcome.mp3";
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("audio", localFilePath)))
                .build();

        MultiModalMessage sysMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                // Configure the context for customized recognition here
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured environment variables, replace the following line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
                .model("qwen3-asr-flash")
                .message(sysMessage)
                .message(userMessage)
                .parameter("asr_options", asrOptions)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }
    public static void main(String[] args) {
        try {
            // 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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

Python SDK

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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {"role": "system", "content": [{"text": ""}]},  # Configure the context for customized recognition
    {"role": "user", "content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}
]
response = dashscope.MultiModalConversation.call(
    # The API keys for the Singapore/US and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
    # If you have not configured environment variables, replace the following line with: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        # "language": "zh", # Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        "enable_itn":False
    },
    stream=True
)

for response in response:
    try:
        print(response["output"]["choices"][0]["message"].content[0]["text"])
    except:
        pass

Java SDK

import java.util.Arrays;
import java.util.Collections;
import java.util.HashMap;
import java.util.Map;

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.common.MultiModalMessage;
import com.alibaba.dashscope.common.Role;
import com.alibaba.dashscope.exception.ApiException;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.alibaba.dashscope.exception.UploadFileException;
import com.alibaba.dashscope.utils.Constants;
import io.reactivex.Flowable;

public class Main {
    public static void simpleMultiModalConversationCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3")))
                .build();

        MultiModalMessage sysMessage = MultiModalMessage.builder().role(Role.SYSTEM.getValue())
                // Configure the context for customized recognition here
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // Optional. If the audio language is known, you can specify it using this parameter to improve recognition accuracy.
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API keys for the Singapore and Beijing regions are different. To obtain an API key, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
                // If you have not configured environment variables, replace the following line with: .apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // If you use a model in the US region, add the "-us" suffix to the model name, for example, qwen3-asr-flash-us
                .model("qwen3-asr-flash")
                .message(sysMessage)
                .message(userMessage)
                .parameter("asr_options", asrOptions)
                .build();
        Flowable<MultiModalConversationResult> resultFlowable = conv.streamCall(param);
        resultFlowable.blockingForEach(item -> {
            try {
                System.out.println(item.getOutput().getChoices().get(0).getMessage().getContent().get(0).get("text"));
            } catch (Exception e){
                System.exit(0);
            }
        });
    }

    public static void main(String[] args) {
        try {
            // 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. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope-intl.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

cURL

# ======= Important =======
# The following URL is for the Singapore region. If you use a model in the US region, replace the URL with: https://dashscope-us.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation. 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, see https://www.alibabacloud.com/help/en/model-studio/get-api-key
# If you use a model in the US region, you must add the "us" suffix.
# === 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-asr-flash",
    "input": {
        "messages": [
            {
                "content": [
                    {
                        "text": ""
                    }
                ],
                "role": "system"
            },
            {
                "content": [
                    {
                        "audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                    }
                ],
                "role": "user"
            }
        ]
    },
    "parameters": {
        "incremental_output": true,
        "asr_options": {
            "enable_itn": false
        }
    }
}'