非实时语音识别（Qwen-ASR）API参考

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 = "{YOUR_AUDIO_FILE}"
    # 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": 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}")

// 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",
});

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("{YOUR_AUDIO_FILE}")}`;

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();

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

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", "{YOUR_AUDIO_URL}")))
                .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，请用阿里云百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-asr-flash")
                .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";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

import os
import dashscope

# 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'

messages = [
    {"role": "user", "content": [{"audio": "{YOUR_AUDIO_URL}"}]}
]

response = dashscope.MultiModalConversation.call(
    # 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，请用阿里云百炼API Key将下行替换为：api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    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)

import base64
import dashscope
import os
import pathlib

# 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'

# 请替换为实际的音频文件路径
file_path = "{YOUR_AUDIO_FILE}"
# 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 = dashscope.MultiModalConversation.call(
    # 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，请用阿里云百炼API Key将下行替换为：api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    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)

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 = "{YOUR_AUDIO_FILE}";
    // 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();

        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，请用阿里云百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-asr-flash")
                .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";
            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;
    }
}

import os
import dashscope

# 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'

# 请用您的本地音频的绝对路径替换 ABSOLUTE_PATH/{YOUR_AUDIO_FILE}
audio_file_path = "file://ABSOLUTE_PATH/{YOUR_AUDIO_FILE}"

messages = [
    {"role": "user", "content": [{"audio": audio_file_path}]}
]
response = dashscope.MultiModalConversation.call(
    # 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，请用阿里云百炼API Key将下行替换为：api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    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)

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/{YOUR_AUDIO_FILE}
        String localFilePath = "file://ABSOLUTE_PATH/{YOUR_AUDIO_FILE}";
        MultiModalConversation conv = new MultiModalConversation();
        MultiModalMessage userMessage = MultiModalMessage.builder()
                .role(Role.USER.getValue())
                .content(Arrays.asList(
                        Collections.singletonMap("audio", localFilePath)))
                .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，请用阿里云百炼API Key将下行替换为：.apiKey("sk-xxx")
                .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                .model("qwen3-asr-flash")
                .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";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}