AI 助理
文档备案控制台
官方文档

录音文件识别（Qwen）

更新时间：
复制 MD 格式
产品详情
我的收藏

一、千问3-ASR-Flash-Filetrans（DashScope 异步调用，长音频）

千问3-ASR-Flash-Filetrans模型专为音频文件的异步转写设计，支持最长12小时录音。该模型要求输入为公网可访问的音频文件URL，不支持直接上传本地文件。此外，它是一个非流式接口，会在任务完成后一次性返回全部识别结果。

cURL - 提交任务

使用 cURL 进行语音识别时，需先提交任务获取任务ID（task_id），再通过该ID获取任务执行结果。

提交任务 

# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription
# 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

curl -X POST 'https://dashscope.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
    }
}'

获取任务执行结果 

# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id}，注意，将{task_id}替换为待查询任务ID
# 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

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

来自 API 参考的 cURL 变体（提交任务）：以下版本使用 --location 参数，且不包含 enable_words 参数：

# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription
# 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

curl --location --request POST 'https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json" \
--header "X-DashScope-Async: enable" \
--data '{
    "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
    }
}'

来自 API 参考的 cURL 变体（获取任务执行结果）：以下版本使用 --location 参数：

# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id}，注意，将{task_id}替换为待查询任务ID
# 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

curl --location --request GET 'https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}' \
--header "Authorization: Bearer $DASHSCOPE_API_KEY" \
--header "Content-Type: application/json"
Java - 完整示例（提交 + 轮询） 
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 {
    // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription
    private static final String API_URL_SUBMIT = "https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription";
    // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/tasks/
    private static final String API_URL_QUERY = "https://dashscope.aliyuncs.com/api/v1/tasks/";
    private static final Gson gson = new Gson();

    public static void main(String[] args) {
        // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        // 若没有配置环境变量，请用百炼API Key将下行替换为：String apiKey = "sk-xxx"
        String apiKey = System.getenv("DASHSCOPE_API_KEY");

        OkHttpClient client = new OkHttpClient();

        // 1. 提交任务
        /*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("任务已提交，task_id: " + taskId);
                } else {
                    System.out.println("提交返回内容: " + respBody);
                    return;
                }
            } else {
                System.out.println("任务提交失败! HTTP code: " + response.code());
                if (response.body() != null) {
                    System.out.println(response.body().string());
                }
                return;
            }
        } catch (IOException e) {
            e.printStackTrace();
            return;
        }

        // 2. 轮询任务状态
        boolean finished = false;
        while (!finished) {
            try {
                TimeUnit.SECONDS.sleep(2);  // 等待 2 秒再查询
            } 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("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("当前任务状态: " + status);
                        if ("SUCCEEDED".equalsIgnoreCase(status)
                                || "FAILED".equalsIgnoreCase(status)
                                || "UNKNOWN".equalsIgnoreCase(status)) {
                            finished = true;
                            System.out.println("任务完成，最终结果: ");
                            System.out.println(queryResponse);
                        }
                    } else {
                        System.out.println("查询返回内容: " + 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;
    }
}

来自 API 参考的 Java 变体（仅提交任务部分）：以下版本仅负责提交任务，不包含轮询逻辑：

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

import java.io.IOException;

public class Main {
    // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription
    private static final String API_URL = "https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription";

    public static void main(String[] args) {
        // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        // 若没有配置环境变量，请用百炼API Key将下行替换为：String apiKey = "sk-xxx"
        String apiKey = System.getenv("DASHSCOPE_API_KEY");

        OkHttpClient client = new OkHttpClient();
        Gson gson = new Gson();

        /*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",
                        "corpus": {
                            "text": ""
                        }
                    }
                }
                """;*/
        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
                    }
                }
                """;

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

        try (Response response = client.newCall(request).execute()) {
            if (response.isSuccessful() && response.body() != null) {
                String respBody = response.body().string();
                // 用 Gson 解析 JSON
                ApiResponse apiResp = gson.fromJson(respBody, ApiResponse.class);
                if (apiResp.output != null) {
                    System.out.println("task_id: " + apiResp.output.taskId);
                } else {
                    System.out.println(respBody);
                }
            } else {
                System.out.println("task failed! HTTP code: " + response.code());
                if (response.body() != null) {
                    System.out.println(response.body().string());
                }
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }

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

        Output output;
    }

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

        @SerializedName("task_status")
        String taskStatus;
    }
}

来自 API 参考的 Java 变体（仅获取任务执行结果）：

import okhttp3.*;

import java.io.IOException;

public class Main {
    public static void main(String[] args) {
        // 替换为实际的task_id
        String taskId = "xxx";
        // 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        // 若没有配置环境变量，请用百炼API Key将下行替换为：String apiKey = "sk-xxx"
        String apiKey = System.getenv("DASHSCOPE_API_KEY");

        // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id}，注意，将{task_id}替换为待查询任务ID
        String apiUrl = "https://dashscope.aliyuncs.com/api/v1/tasks/" + taskId;

        OkHttpClient client = new OkHttpClient();

        Request request = new Request.Builder()
                .url(apiUrl)
                .addHeader("Authorization", "Bearer " + apiKey)
                .addHeader("Content-Type", "application/json")
                .get()
                .build();

        try (Response response = client.newCall(request).execute()) {
            if (response.body() != null) {
                System.out.println(response.body().string());
            }
        } catch (IOException e) {
            e.printStackTrace();
        }
    }
}
Python - 完整示例（提交 + 轮询） 
import os
import time
import requests
import json

# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription
API_URL_SUBMIT = "https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription"
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/tasks/
API_URL_QUERY_BASE = "https://dashscope.aliyuncs.com/api/v1/tasks/"

def main():
    # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用百炼API Key将下行替换为：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. 提交任务
    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("提交 ASR 转写任务...")
    try:
        submit_resp = requests.post(API_URL_SUBMIT, headers=headers, data=json.dumps(payload))
    except requests.RequestException as e:
        print(f"请求提交任务失败: {e}")
        return

    if submit_resp.status_code != 200:
        print(f"任务提交失败! 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("提交返回内容异常:", resp_data)
        return

    task_id = output["task_id"]
    print(f"任务已提交，task_id: {task_id}")

    # 2. 轮询任务状态
    finished = False
    while not finished:
        time.sleep(2)  # 等待 2 秒再查询

        query_url = API_URL_QUERY_BASE + task_id
        try:
            query_resp = requests.get(query_url, headers={"Authorization": f"Bearer {api_key}"})
        except requests.RequestException as e:
            print(f"请求查询任务失败: {e}")
            return

        if query_resp.status_code != 200:
            print(f"查询任务失败! 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"当前任务状态: {status}")

            if status.upper() in ("SUCCEEDED", "FAILED", "UNKNOWN"):
                finished = True
                print("任务完成，最终结果如下：")
                print(json.dumps(query_data, indent=2, ensure_ascii=False))
        else:
            print("查询返回内容:", query_data)

if __name__ == "__main__":
    main()

来自 API 参考的 Python 变体（仅提交任务部分）：以下版本仅负责提交任务，不包含轮询逻辑：

import requests
import json
import os

# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/audio/asr/transcription
url = "https://dashscope.aliyuncs.com/api/v1/services/audio/asr/transcription"

# 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# 若没有配置环境变量，请用百炼API Key将下行替换为：DASHSCOPE_API_KEY = "sk-xxx"
DASHSCOPE_API_KEY = os.getenv("DASHSCOPE_API_KEY")

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

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
        # "corpus": {
        #     "text": ""
        # }
    }
}

response = requests.post(url, headers=headers, data=json.dumps(payload))
if response.status_code == 200:
    print(f"task_id: {response.json()["output"]["task_id"]}")
else:
    print("task failed!")
    print(response.json())

来自 API 参考的 Python 变体（仅获取任务执行结果）：

import os
import requests

# 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# 若没有配置环境变量，请用百炼API Key将下行替换为：DASHSCOPE_API_KEY = "sk-xxx"
DASHSCOPE_API_KEY = os.getenv("DASHSCOPE_API_KEY")

# 替换为实际的task_id
task_id = "xxx"
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/tasks/{task_id}，注意，将{task_id}替换为待查询任务ID
url = f"https://dashscope.aliyuncs.com/api/v1/tasks/{task_id}"

headers = {
    "Authorization": f"Bearer {DASHSCOPE_API_KEY}",
    "Content-Type": "application/json"
}

response = requests.get(url, headers=headers)
print(response.json())
Java SDK 
import com.alibaba.dashscope.audio.qwen_asr.*;
import com.alibaba.dashscope.utils.Constants;
import com.google.gson.Gson;
import com.google.gson.GsonBuilder;
import com.google.gson.JsonObject;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.ArrayList;
import java.util.HashMap;

public class Main {
    public static void main(String[] args) {
        // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1
        Constants.baseHttpApiUrl = "https://dashscope.aliyuncs.com/api/v1";
        QwenTranscriptionParam param =
                QwenTranscriptionParam.builder()
                        // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
                        // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model("qwen3-asr-flash-filetrans")
                        .fileUrl("https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/sensevoice/rich_text_example_1.wav")
                        //.parameter("language", "zh")
                        //.parameter("channel_id", new ArrayList<String>(){{add("0");add("1");}})
                        .parameter("enable_itn", false)
                        .parameter("enable_words", true)
                        .build();
        try {
            QwenTranscription transcription = new QwenTranscription();
            // 提交任务
            QwenTranscriptionResult result = transcription.asyncCall(param);
            System.out.println("create task result: " + result);
            // 查询任务状态
            result = transcription.fetch(QwenTranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            System.out.println("task status: " + result);
            // 等待任务完成
            result =
                    transcription.wait(
                            QwenTranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            System.out.println("task result: " + result);
            // 获取语音识别结果
            QwenTranscriptionTaskResult taskResult = result.getResult();
            if (taskResult != null) {
                // 获取识别结果的url
                String transcriptionUrl = taskResult.getTranscriptionUrl();
                // 获取url内对应的结果
                HttpURLConnection connection =
                        (HttpURLConnection) new URL(transcriptionUrl).openConnection();
                connection.setRequestMethod("GET");
                connection.connect();
                BufferedReader reader =
                        new BufferedReader(new InputStreamReader(connection.getInputStream()));
                // 格式化输出json结果
                Gson gson = new GsonBuilder().setPrettyPrinting().create();
                System.out.println(gson.toJson(gson.fromJson(reader, JsonObject.class)));
            }
        } catch (Exception e) {
            System.out.println("error: " + e);
        }
    }
}
Python SDK 
import os

import dashscope

# run the transcription script
if __name__ == '__main__':
    # 以下为北京地域（region默认为cn-beijing）。若使用新加坡地域的模型，需将region替换为：ap-southeast-1，若使用美国地域的模型，需将region替换为：us-east-1
    client = dashscope.Client(
        # 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
        api_key=os.getenv("DASHSCOPE_API_KEY"),
    )

    # 提交录音文件识别任务
    job = client.audio.asr.jobs.create(
        model='qwen3-asr-flash-filetrans',
        file_urls=['https://dashscope.oss-cn-beijing.aliyuncs.com/samples/audio/sensevoice/rich_text_example_1.wav'],
        parameters={
            # 'language': '',  # 可选，指定待识别语种
            'enable_itn': False,
            'enable_words': True
        }
    )
    print(f'task_response: {job}')
    print(job.task_id)
    # 查询任务状态
    query_response = client.audio.asr.jobs.fetch(job.task_id)
    print(f'query_response: {query_response}')
    # 等待任务完成
    task_result = client.audio.asr.jobs.wait(job)
    print(f'task_result: {task_result}')

二、千问3-ASR-Flash（DashScope 同步调用，短音频）

千问3-ASR-Flash模型支持最长5分钟录音。该模型可输入公网可访问的音频文件URL或直接上传本地文件。此外，它可流式返回识别结果。

输入内容：音频文件URL
Python SDK 
import os
import dashscope

# 以下为北京地域（region默认为cn-beijing）。若使用新加坡地域的模型，需将region替换为：ap-southeast-1，若使用美国地域的模型，需将region替换为：us-east-1
client = dashscope.Client(
    # 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

messages = [
    {"role": "user", "content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}
]

response = client.multimodal.chat.create(
    model="qwen3-asr-flash",
    messages=messages,
    parameters={
        "asr_options": {
            # "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
            "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())
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();
        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .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 {
            // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1，若使用美国地域的模型，需将url替换为：https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}
cURL 
# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation，若使用美国地域的模型，需将url替换为：https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

curl -X POST "https://dashscope.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
        }
    }
}'
输入内容：Base64编码的音频文件

Base64 编码辅助代码 

Python

import base64, pathlib

# input.mp3为待识别的本地音频文件，请替换为自己的音频文件路径，确保其符合音频要求
file_path = pathlib.Path("input.mp3")
base64_str = base64.b64encode(file_path.read_bytes()).decode()
data_uri = f"data:audio/mpeg;base64,{base64_str}"

Java

import java.nio.file.*;
import java.util.Base64;

public class Main {
    /**
     * filePath 为待识别的本地音频文件，请替换为自己的音频文件路径，确保其符合音频要求。
     */
    public static String toDataUrl(String filePath) throws Exception {
        byte[] bytes = Files.readAllBytes(Paths.get(filePath));
        String encoded = Base64.getEncoder().encodeToString(bytes);
        return "data:audio/mpeg;base64," + encoded;
    }

    // 使用示例
    public static void main(String[] args) throws Exception {
        System.out.println(toDataUrl("input.mp3"));
    }
}
Python SDK

示例中用到的音频文件为：welcome.mp3。

import base64
import dashscope
import os
import pathlib

# 以下为北京地域（region默认为cn-beijing）。若使用新加坡地域的模型，需将region替换为：ap-southeast-1，若使用美国地域的模型，需将region替换为：us-east-1
client = dashscope.Client(
    # 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

# 请替换为实际的音频文件路径
file_path = "welcome.mp3"
# 请替换为实际的音频文件MIME类型
audio_mime_type = "audio/mpeg"

file_path_obj = pathlib.Path(file_path)
if not file_path_obj.exists():
    raise FileNotFoundError(f"音频文件不存在: {file_path}")

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

messages = [
    {"role": "user", "content": [{"audio": data_uri}]}
]
response = client.multimodal.chat.create(
    model="qwen3-asr-flash",
    messages=messages,
    parameters={
        "asr_options": {
            # "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
            "enable_itn":False
        }
    }
)
print(response)
Java SDK

示例中用到的音频文件为：welcome.mp3。

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 {
    // 请替换为实际的音频文件路径
    private static final String AUDIO_FILE = "welcome.mp3";
    // 请替换为实际的音频文件MIME类型
    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())
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();
        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .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 {
            // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1，若使用美国地域的模型，需将url替换为：https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }

    // 生成 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;
    }
}
输入内容：本地音频文件绝对路径
Python SDK

示例中用到的音频文件为：welcome.mp3。

import os
import dashscope

# 以下为北京地域（region默认为cn-beijing）。若使用新加坡地域的模型，需将region替换为：ap-southeast-1，若使用美国地域的模型，需将region替换为：us-east-1
client = dashscope.Client(
    # 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

# 请用您的本地音频的绝对路径替换 ABSOLUTE_PATH/welcome.mp3
audio_file_path = "file://ABSOLUTE_PATH/welcome.mp3"

messages = [
    {"role": "user", "content": [{"audio": audio_file_path}]}
]
response = client.multimodal.chat.create(
    model="qwen3-asr-flash",
    messages=messages,
    parameters={
        "asr_options": {
            # "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
            "enable_itn":False
        }
    }
)
print(response)
Java SDK

示例中用到的音频文件为：welcome.mp3。

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 {
        // 请用您本地文件的绝对路径替换掉ABSOLUTE_PATH/welcome.mp3
        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())
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .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 {
            // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1，若使用美国地域的模型，需将url替换为：https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}
流式输出
Python SDK 
import os
import dashscope

# 以下为北京地域（region默认为cn-beijing）。若使用新加坡地域的模型，需将region替换为：ap-southeast-1，若使用美国地域的模型，需将region替换为：us-east-1
client = dashscope.Client(
    # 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

messages = [
    {"role": "user", "content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}
]
stream = client.multimodal.chat.create(
    model="qwen3-asr-flash",
    messages=messages,
    parameters={
        "asr_options": {
            # "language": "zh", # 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
            "enable_itn":False
        }
    },
    stream=True
)

for chunk in stream:
    delta = chunk.choices[0].delta
    if delta.content:
        print(delta.content)
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())
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();
        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // 可选，若已知音频的语种，可通过该参数指定待识别语种，以提升识别准确率
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
                // 若没有配置环境变量，请用百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .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 {
            // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1，若使用美国地域的模型，需将url替换为：https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1
            Constants.baseHttpApiUrl = "https://dashscope.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}
cURL 
# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation，若使用美国地域的模型，需将url替换为：https://{WorkspaceId}.us-east-1.maas.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# 新加坡/美国地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

curl -X POST "https://dashscope.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
        }
    }
}'

三、千问Audio ASR（Beta，DashScope 同步调用）

千问Audio ASR模型为Beta版本，功能有限，且不保证服务稳定，仅供体验。生产环境请务必使用千问3-ASR-Flash-Filetrans或千问3-ASR-Flash。

输入内容：音频文件URL
Python SDK 
import os
import dashscope

client = dashscope.Client(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

messages = [{"role": "user","content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}]
response = client.multimodal.chat.create(
    model="qwen3.5-omni-plus",
    messages=messages)
print(response)
Java SDK 
import java.util.Arrays;
import java.util.Collections;

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.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();

        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen3.5-omni-plus")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }
    public static void main(String[] args) {
        try {
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}
cURL 
curl -X POST https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3.5-omni-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}
                ]
            }
        ]
    }
}'
输入内容：本地音频文件绝对路径
Python SDK 
import os
import dashscope

client = dashscope.Client(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

# 请用您的本地音频的绝对路径替换 ABSOLUTE_PATH/welcome.mp3
audio_file_path = "file://ABSOLUTE_PATH/welcome.mp3"
messages = [{"role": "user","content": [{"audio": audio_file_path}]}]

response = client.multimodal.chat.create(model="qwen3.5-omni-plus", messages=messages)
print(response)
Java SDK 
import java.util.Arrays;
import java.util.HashMap;

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.JsonUtils;

public class Main {
    public static void callWithLocalFile()
            throws ApiException, NoApiKeyException, UploadFileException {
        // 请用您本地文件的绝对路径替换掉ABSOLUTE_PATH/welcome.mp3
        String localFilePath = "file://ABSOLUTE_PATH/welcome.mp3";
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("audio", localFilePath);}}))
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen3.5-omni-plus")
                .message(userMessage)
                .build();
        MultiModalConversationResult result = conv.call(param);
        System.out.println(JsonUtils.toJson(result));
    }
    public static void main(String[] args) {
        try {callWithLocalFile();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}
流式输出
Python SDK 
import os
import dashscope

client = dashscope.Client(
    # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key="sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
)

messages = [{"role": "user", "content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}]

stream = client.multimodal.chat.create(
    model="qwen3.5-omni-plus",
    messages=messages,
    stream=True)
full_content = ""
print("流式输出内容为：")
for chunk in stream:
    delta = chunk.choices[0].delta
    if delta.content:
        print(delta.content)
        full_content += delta.content
print(f"完整内容为：{full_content}")
Java SDK 
import java.util.Arrays;
import java.util.HashMap;

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 io.reactivex.Flowable;

public class Main {
    public static void streamCall()
            throws ApiException, NoApiKeyException, UploadFileException {
        MultiModalConversation conv = new MultiModalConversation();// must create mutable map.
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(new HashMap<String, Object>(){{put("audio", "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3");}}))
                .build();
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                .model("qwen3.5-omni-plus")
                .message(userMessage)
                .incrementalOutput(true)
                .build();
        Flowable<MultiModalConversationResult> result = conv.streamCall(param);
        result.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 {streamCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}
cURL 
curl -X POST "https://dashscope.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": "qwen3.5-omni-plus",
    "input":{
        "messages":[
            {
                "role": "user",
                "content": [
                    {"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}
                ]
            }
        ]
    },
    "parameters": {
      "incremental_output": true
    }
}'

四、OpenAI 兼容方式（仅千问3-ASR-Flash）

仅千问3-ASR-Flash系列模型支持OpenAI兼容方式调用。OpenAI兼容方式支持输入公网可访问的音频文件URL或Base64编码的音频数据，不支持输入本地音频文件绝对路径。

OpenAI Python SDK 版本应不低于1.52.0， Node.js SDK 版本应不低于 4.68.0。

asr_options不是OpenAI标准参数。使用OpenAI Python SDK时，通过extra_body传入；使用Node.js SDK时，将asr_options放在请求对象顶层。

输入内容：音频文件URL
Python SDK 
from openai import OpenAI
import os

try:
    client = OpenAI(
        # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
    )

    stream_enabled = False  # 是否开启流式输出
    completion = client.chat.completions.create(
        model="qwen3-asr-flash",
        messages=[
            {
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                        }
                    }
                ],
                "role": "user"
            }
        ],
        stream=stream_enabled,
        # stream设为False时，不能设置stream_options参数
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("流式输出内容为：")
        for chunk in completion:
            # 如果stream_options.include_usage为True，则最后一个chunk的choices字段为空列表，需要跳过（可以通过chunk.usage获取 Token 使用量）
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"完整内容为：{full_content}")
    else:
        print(f"非流式输出内容为：{completion.choices[0].message.content}")
except Exception as e:
    print(f"错误信息：{e}")
Node.js SDK 
// 运行前的准备工作:
// Windows/Mac/Linux 通用:
// 1. 确保已安装 Node.js (建议版本 >= 14)
// 2. 运行以下命令安装必要的依赖: npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
  // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1",
});

async function main() {
  try {
    const streamEnabled = false; // 是否开启流式输出
    const completion = await client.chat.completions.create({
      model: "qwen3-asr-flash",
      messages: [
        {
          role: "user",
          content: [
            {
              type: "input_audio",
              input_audio: {
                data: "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
              }
            }
          ]
        }
      ],
      stream: streamEnabled,
      // stream设为False时，不能设置stream_options参数
      // stream_options: {
      //   "include_usage": true
      // },
      asr_options: {
        // language: "zh",
        enable_itn: false
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("流式输出内容为：");
      for await (const chunk of completion) {
        console.log(JSON.stringify(chunk));
        if (chunk.choices && chunk.choices.length > 0) {
          const delta = chunk.choices[0].delta;
          if (delta && delta.content) {
            fullContent += delta.content;
          }
        }
      }
      console.log(`完整内容为：${fullContent}`);
    } else {
      console.log(`非流式输出内容为：${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`错误信息：${err}`);
  }
}

main();
cURL 
# ======= 重要提示 =======
# 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1/chat/completions
# 新加坡地域和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
# === 执行时请删除该注释 ===

curl -X POST 'https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions' \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
    "model": "qwen3-asr-flash",
    "messages": [
        {
            "content": [
                {
                    "type": "input_audio",
                    "input_audio": {
                        "data": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"
                    }
                }
            ],
            "role": "user"
        }
    ],
    "stream":false,
    "asr_options": {
        "enable_itn": false
    }
}'
输入内容：Base64编码的音频文件
Python SDK

示例中用到的音频文件为：welcome.mp3。

import base64
from openai import OpenAI
import os
import pathlib

try:
    # 请替换为实际的音频文件路径
    file_path = "welcome.mp3"
    # 请替换为实际的音频文件MIME类型
    audio_mime_type = "audio/mpeg"

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"音频文件不存在: {file_path}")

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

    client = OpenAI(
        # 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
        # 若没有配置环境变量，请用百炼API Key将下行替换为：api_key = "sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope.aliyuncs.com/compatible-mode/v1",
    )

    stream_enabled = False  # 是否开启流式输出
    completion = client.chat.completions.create(
        model="qwen3-asr-flash",
        messages=[
            {
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": data_uri
                        }
                    }
                ],
                "role": "user"
            }
        ],
        stream=stream_enabled,
        # stream设为False时，不能设置stream_options参数
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("流式输出内容为：")
        for chunk in completion:
            # 如果stream_options.include_usage为True，则最后一个chunk的choices字段为空列表，需要跳过（可以通过chunk.usage获取 Token 使用量）
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"完整内容为：{full_content}")
    else:
        print(f"非流式输出内容为：{completion.choices[0].message.content}")
except Exception as e:
    print(f"错误信息：{e}")
Node.js SDK

示例中用到的音频文件为：welcome.mp3。

// 运行前的准备工作:
// Windows/Mac/Linux 通用:
// 1. 确保已安装 Node.js (建议版本 >= 14)
// 2. 运行以下命令安装必要的依赖: npm install openai

import OpenAI from "openai";
import { readFileSync } from 'fs';

const client = new OpenAI({
  // 新加坡和北京地域的API Key不同。获取API Key：https://help.aliyun.com/zh/model-studio/get-api-key
  // 若没有配置环境变量，请用百炼API Key将下行替换为：apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // 以下为北京地域url，若使用新加坡地域的模型，需将url替换为：https://dashscope-intl.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1",
});

const encodeAudioFile = (audioFilePath) => {
    const audioFile = readFileSync(audioFilePath);
    return audioFile.toString('base64');
};

// 请替换为实际的音频文件路径
const dataUri = `data:audio/mpeg;base64,${encodeAudioFile("welcome.mp3")}`;

async function main() {
  try {
    const streamEnabled = false; // 是否开启流式输出
    const completion = await client.chat.completions.create({
      model: "qwen3-asr-flash",
      messages: [
        {
          role: "user",
          content: [
            {
              type: "input_audio",
              input_audio: {
                data: dataUri
              }
            }
          ]
        }
      ],
      stream: streamEnabled,
      // stream设为False时，不能设置stream_options参数
      // stream_options: {
      //   "include_usage": true
      // },
      asr_options: {
        // language: "zh",
        enable_itn: false
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("流式输出内容为：");
      for await (const chunk of completion) {
        console.log(JSON.stringify(chunk));
        if (chunk.choices && chunk.choices.length > 0) {
          const delta = chunk.choices[0].delta;
          if (delta && delta.content) {
            fullContent += delta.content;
          }
        }
      }
      console.log(`完整内容为：${fullContent}`);
    } else {
      console.log(`非流式输出内容为：${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`错误信息：${err}`);
  }
}

main();