Alibaba Cloud Model Studio：錄音檔案識別（Qwen-ASR）API參考

Python SDK

from openai import OpenAI
import os

try:
    client = OpenAI(
        # 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        # 若沒有配置環境變數，請用百鍊API Key將下行替換為：api_key = "sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # 以下為新加坡/美國地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
    )
    

    stream_enabled = False  # 是否開啟流式輸出
    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設為False時，不能設定stream_options參數
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("流式輸出內容為：")
        for chunk in completion:
            # 如果stream_options.include_usage為True，則最後一個chunk的choices欄位為空白列表，需要跳過（可以通過chunk.usage擷取 Token 使用量）
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"完整內容為：{full_content}")
    else:
        print(f"非流式輸出內容為：{completion.choices[0].message.content}")
except Exception as e:
    print(f"錯誤資訊：{e}")

Node.js SDK

// 運行前的準備工作:
// Windows/Mac/Linux 通用:
// 1. 確保已安裝 Node.js (建議版本 >= 14)
// 2. 運行以下命令安裝必要的依賴: npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  // 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
  // 若沒有配置環境變數，請用百鍊API Key將下行替換為：apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // 以下為新加坡/美國地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", 
});

async function main() {
  try {
    const streamEnabled = false; // 是否開啟流式輸出
    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設為False時，不能設定stream_options參數
      // stream_options: {
      //   "include_usage": true
      // },
      extra_body: {
        asr_options: {
          // language: "zh",
          enable_itn: false
        }
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("流式輸出內容為：");
      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(`完整內容為：${fullContent}`);
    } else {
      console.log(`非流式輸出內容為：${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`錯誤資訊：${err}`);
  }
}

main();

cURL

# ======= 重要提示 =======
# 以下為新加坡/美國地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# === 執行時請刪除該注釋 ===

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

Python SDK

import base64
from openai import OpenAI
import os
import pathlib

try:
    # 請替換為實際的音頻檔案路徑
    file_path = "welcome.mp3"
    # 請替換為實際的音頻檔案MIME類型
    audio_mime_type = "audio/mpeg"

    file_path_obj = pathlib.Path(file_path)
    if not file_path_obj.exists():
        raise FileNotFoundError(f"音頻檔案不存在: {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/美國和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
        # 若沒有配置環境變數，請用百鍊API Key將下行替換為：api_key = "sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # 以下為新加坡/美國地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
    )
    

    stream_enabled = False  # 是否開啟流式輸出
    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設為False時，不能設定stream_options參數
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("流式輸出內容為：")
        for chunk in completion:
            # 如果stream_options.include_usage為True，則最後一個chunk的choices欄位為空白列表，需要跳過（可以通過chunk.usage擷取 Token 使用量）
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"完整內容為：{full_content}")
    else:
        print(f"非流式輸出內容為：{completion.choices[0].message.content}")
except Exception as e:
    print(f"錯誤資訊：{e}")

Node.js SDK

// 運行前的準備工作:
// Windows/Mac/Linux 通用:
// 1. 確保已安裝 Node.js (建議版本 >= 14)
// 2. 運行以下命令安裝必要的依賴: npm install openai

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

const client = new OpenAI({
  // 新加坡/美國和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
  // 若沒有配置環境變數，請用百鍊API Key將下行替換為：apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // 以下為新加坡/美國地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", 
});

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

// 請替換為實際的音頻檔案路徑
const dataUri = `data:audio/mpeg;base64,${encodeAudioFile("welcome.mp3")}`;

async function main() {
  try {
    const streamEnabled = false; // 是否開啟流式輸出
    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設為False時，不能設定stream_options參數
      // stream_options: {
      //   "include_usage": true
      // },
      extra_body: {
        asr_options: {
          // language: "zh",
          enable_itn: false
        }
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("流式輸出內容為：");
      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(`完整內容為：${fullContent}`);
    } else {
      console.log(`非流式輸出內容為：${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`錯誤資訊：${err}`);
  }
}

main();

cURL

# ======= 重要提示 =======
# 以下為新加坡地區url若使用美國地區的模型，需將url替換為：https://dashscope-us.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1/services/aigc/multimodal-generation/generation
# 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# 若使用美國地區的模型，需要加us尾碼
# === 執行時請刪除該注釋 ===

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
        }
    }
}'

Java

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())
                // 此處用於配置定製化識別的Context
                .content(Arrays.asList(Collections.singletonMap("text", "")))
                .build();

        Map<String, Object> asrOptions = new HashMap<>();
        asrOptions.put("enable_itn", false);
        // asrOptions.put("language", "zh"); // 可選，若已知音訊語種，可通過該參數指定待識別語種，以提升識別準確率
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                // 若沒有配置環境變數，請用百鍊API Key將下行替換為：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                // 若使用美國地區的模型，需在模型後面加上“-us”尾碼，例如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 {
            // 以下為新加坡地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1，若使用美國地區的模型，需將url替換為：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

import os
import dashscope

# 以下為新加坡地區url，若使用北京地區的模型，需將url替換為：https://dashscope.aliyuncs.com/api/v1，若使用美國地區的模型，需將url替換為：https://dashscope-us.aliyuncs.com/api/v1
dashscope.base_http_api_url = 'https://dashscope-intl.aliyuncs.com/api/v1'

messages = [
    {"role": "system", "content": [{"text": ""}]},  # 配置定製化識別的 Context
    {"role": "user", "content": [{"audio": "https://dashscope.oss-cn-beijing.aliyuncs.com/audios/welcome.mp3"}]}
]

response = dashscope.MultiModalConversation.call(
    # 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
    # 若沒有配置環境變數，請用百鍊API Key將下行替換為：api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    # 若使用美國地區的模型，需在模型後面加上“-us”尾碼，例如qwen3-asr-flash-us
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        #"language": "zh", # 可選，若已知音訊語種，可通過該參數指定待識別語種，以提升識別準確率
        "enable_itn":False
    }
)
print(response)