非实时语音识别

cURL

使用 cURL 调用时，先提交任务获取 task_id，再通过该 ID 查询任务执行结果。

curl -X POST 'https://{WorkspaceId}.cn-beijing.maas.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": "qwen-audio-3.1-asr-flash-filetrans",
    "input": {
        "file_urls": [
            "{YOUR_AUDIO_URL}"
        ]
    },
    "parameters": {
        "channel_id": [0],
        "language_hints": ["zh", "en"]
    }
}'

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

# 将 {transcription_url} 替换为查询接口返回的 transcription_url 值
curl -sS '{transcription_url}' -o transcription.json
cat transcription.json | jq .

Python

from http import HTTPStatus
from dashscope.audio.asr import Transcription
from urllib import request
import dashscope
import os
import json

# 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1'

# 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，请用阿里云百炼API Key将下行替换为：dashscope.api_key = "sk-xxx"
dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")

task_response = Transcription.async_call(
    model='qwen-audio-3.1-asr-flash-filetrans',
    file_urls=['{YOUR_AUDIO_URL}'],
    language_hints=['zh', 'en']  # language_hints为可选参数，用于指定待识别音频的语言代码。取值范围请参见API参考文档。
)

transcription_response = Transcription.wait(task=task_response.output.task_id)

if transcription_response.status_code == HTTPStatus.OK:
    for transcription in transcription_response.output['results']:
        if transcription['subtask_status'] == 'SUCCEEDED':
            url = transcription['transcription_url']
            result = json.loads(request.urlopen(url).read().decode('utf8'))
            print(json.dumps(result, indent=4,
                            ensure_ascii=False))
        else:
            print('transcription failed!')
            print(transcription)
else:
        print('Error: ', transcription_response.output.message)

Java

import com.alibaba.dashscope.audio.asr.transcription.*;
import com.alibaba.dashscope.utils.Constants;
import com.google.gson.*;

import java.io.BufferedReader;
import java.io.InputStreamReader;
import java.net.HttpURLConnection;
import java.net.URL;
import java.util.Arrays;
import java.util.List;

public class Main {
    public static void main(String[] args) {
        // 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.cn-beijing.maas.aliyuncs.com/api/v1";
        // 创建转写请求参数。
        TranscriptionParam param =
                TranscriptionParam.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，请用阿里云百炼API Key将下行替换为：.apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model("qwen-audio-3.1-asr-flash-filetrans")
                        // language_hints为可选参数，用于指定待识别音频的语言代码。取值范围请参见API参考文档。
                        .parameter("language_hints", new String[]{"zh", "en"})
                        .fileUrls(
                                Arrays.asList(
                                        "{YOUR_AUDIO_URL}"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // 提交转写请求
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // 检查任务是否提交成功
            if (result.getTaskId() == null) {
                System.out.println("Error: " + result.getOutput());
                System.exit(1);
            }
            // 阻塞等待任务完成并获取结果
            result = transcription.wait(
                    TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            // 获取转写结果
            List<TranscriptionTaskResult> taskResultList = result.getResults();
            if (taskResultList != null && taskResultList.size() > 0) {
                for (TranscriptionTaskResult taskResult : taskResultList) {
                    String transcriptionUrl = taskResult.getTranscriptionUrl();
                    HttpURLConnection connection =
                            (HttpURLConnection) new URL(transcriptionUrl).openConnection();
                    connection.setRequestMethod("GET");
                    connection.connect();
                    BufferedReader reader =
                            new BufferedReader(new InputStreamReader(connection.getInputStream()));
                    Gson gson = new GsonBuilder().setPrettyPrinting().create();
                    JsonElement jsonResult = gson.fromJson(reader, JsonObject.class);
                    System.out.println(gson.toJson(jsonResult));
                }
            }
        } catch (Exception e) {
            System.out.println("error: " + e);
        }
        System.exit(0);
    }
}

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，请用阿里云百炼API Key将下行替换为：api_key = "sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
        base_url="https://{WorkspaceId}.cn-beijing.maas.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": "{YOUR_AUDIO_URL}"
                        }
                    }
                ],
                "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，请用阿里云百炼API Key将下行替换为：apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // 以下为华北2（北京）地域的配置，调用时请将"{WorkspaceId}"替换为真实的业务空间ID，各地域的配置不同。
  baseURL: "https://{WorkspaceId}.cn-beijing.maas.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: "{YOUR_AUDIO_URL}"
              }
            }
          ]
        }
      ],
      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

以下为华北2（北京）地域的配置，调用时请将{WorkspaceId}替换为真实的Workspace ID，各地域的配置不同。

curl -X POST 'https://{WorkspaceId}.cn-beijing.maas.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": "{YOUR_AUDIO_URL}"
                    }
                }
            ],
            "role": "user"
        }
    ],
    "stream":false,
    "asr_options": {
        "enable_itn": false
    }
}'