Alibaba Cloud Model Studio:Audio file recognition (Qwen-ASR) API reference

Python SDK

from openai import OpenAI
import os

try:
    client = OpenAI(
        # 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"),
        # The following URL is for the Singapore/US region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
    )
    

    stream_enabled = False  # Whether to enable streaming output
    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,
        # When stream is set to False, you cannot set the stream_options parameter.
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("Streaming output content:")
        for chunk in completion:
            # If stream_options.include_usage is True, the choices field of the last chunk is an empty list and should be skipped. You can get token usage from chunk.usage.
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"Full content: {full_content}")
    else:
        print(f"Non-streaming output content: {completion.choices[0].message.content}")
except Exception as e:
    print(f"Error message: {e}")

Node.js SDK

// Preparations:
// For Windows/Mac/Linux:
// 1. Make sure Node.js is installed (version >= 14 is recommended).
// 2. Run the following command to install the necessary dependencies: npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  // 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: process.env.DASHSCOPE_API_KEY,
  // The following URL is for the Singapore/US region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
  baseURL: "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", 
});

async function main() {
  try {
    const streamEnabled = false; // Whether to enable streaming output
    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,
      // When stream is set to False, you cannot set the stream_options parameter.
      // stream_options: {
      //   "include_usage": true
      // },
      extra_body: {
        asr_options: {
          // language: "zh",
          enable_itn: false
        }
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("Streaming output content:");
      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(`Full content: ${fullContent}`);
    } else {
      console.log(`Non-streaming output content: ${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`Error message: ${err}`);
  }
}

main();

cURL

# ======= Important =======
# The following URL is for the Singapore/US region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions
# 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
# === Delete this comment before execution ===

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:
    # 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}"

    client = OpenAI(
        # 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"),
        # The following URL is for the Singapore/US region. If you use a model in the Beijing region, replace the URL with: https://dashscope.aliyuncs.com/compatible-mode/v1
        base_url="https://dashscope-intl.aliyuncs.com/compatible-mode/v1",
    )
    

    stream_enabled = False  # Whether to enable streaming output
    completion = client.chat.completions.create(
        model="qwen3-asr-flash",
        messages=[
            {
                "content": [
                    {
                        "type": "input_audio",
                        "input_audio": {
                            "data": data_uri
                        }
                    }
                ],
                "role": "user"
            }
        ],
        stream=stream_enabled,
        # When stream is set to False, you cannot set the stream_options parameter.
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("Streaming output content:")
        for chunk in completion:
            # If stream_options.include_usage is True, the choices field of the last chunk is an empty list and should be skipped. You can get token usage from chunk.usage.
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"Full content: {full_content}")
    else:
        print(f"Non-streaming output content: {completion.choices[0].message.content}")
except Exception as e:
    print(f"Error message: {e}")

Node.js SDK

// Preparations:
// For Windows/Mac/Linux:
// 1. Make sure Node.js is installed (version >= 14 is recommended).
// 2. Run the following command to install the necessary dependencies: npm install openai

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

const client = new OpenAI({
  // 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: process.env.DASHSCOPE_API_KEY,
  // The following URL is for the Singapore/US region. If you use a model in the Beijing region, replace the URL with: 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');
};

// Replace with the actual path to your audio file
const dataUri = `data:audio/mpeg;base64,${encodeAudioFile("welcome.mp3")}`;

async function main() {
  try {
    const streamEnabled = false; // Whether to enable streaming output
    const completion = await client.chat.completions.create({
      model: "qwen3-asr-flash",
      messages: [
        {
          role: "user",
          content: [
            {
              type: "input_audio",
              input_audio: {
                data: dataUri
              }
            }
          ]
        }
      ],
      stream: streamEnabled,
      // When stream is set to False, you cannot set the stream_options parameter.
      // stream_options: {
      //   "include_usage": true
      // },
      extra_body: {
        asr_options: {
          // language: "zh",
          enable_itn: false
        }
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("Streaming output content:");
      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(`Full content: ${fullContent}`);
    } else {
      console.log(`Non-streaming output content: ${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`Error message: ${err}`);
  }
}

main();

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
        }
    }
}'

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())
                // 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);
    }
}

Python

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)