Alibaba Cloud Model Studio:Referencia de la API de reconocimiento de voz no en tiempo real (Qwen-ASR)

import base64
from openai import OpenAI
import os
import pathlib

try:
    # Replace with the actual audio file path
    file_path = "{YOUR_AUDIO_FILE}"
    # Replace with the actual MIME type of the 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 does not exist: {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 Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
        # If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: api_key = "sk-xxx",
        api_key=os.getenv("DASHSCOPE_API_KEY"),
        # The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
        base_url="https://{WorkspaceId}.ap-southeast-1.maas.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, the stream_options parameter cannot be set
        # stream_options={"include_usage": True},
        extra_body={
            "asr_options": {
                # "language": "zh",
                "enable_itn": False
            }
        }
    )
    if stream_enabled:
        full_content = ""
        print("The streaming output is:")
        for chunk in completion:
            # If stream_options.include_usage is True, the choices field of the last chunk is an empty list and needs to be skipped (you can get the Token usage via chunk.usage)
            print(chunk)
            if chunk.choices and chunk.choices[0].delta.content:
                full_content += chunk.choices[0].delta.content
        print(f"The complete content is: {full_content}")
    else:
        print(f"The non-streaming output is: {completion.choices[0].message.content}")
except Exception as e:
    print(f"Error message: {e}")

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

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

const client = new OpenAI({
  // The API Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
  // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
  baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
});

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

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

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, the stream_options parameter cannot be set
      // stream_options: {
      //   "include_usage": true
      // },
      asr_options: {
        // language: "zh",
        enable_itn: false
      }
    });

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

main();

curl -X POST "https://{WorkspaceId}.ap-southeast-1.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"); // Optional. If you know the language of the audio, you can use this parameter to specify the language to recognize, to improve recognition accuracy
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
                // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: .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 {
            // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
            Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}

import os
import dashscope

# The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

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

response = dashscope.MultiModalConversation.call(
    # The API Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        #"language": "zh", # Optional. If you know the language of the audio, you can use this parameter to specify the language to recognize, to improve recognition accuracy
        "enable_itn":False
    }
)
print(response)

import base64
import dashscope
import os
import pathlib

# The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# Replace with the actual audio file path
file_path = "{YOUR_AUDIO_FILE}"
# Replace with the actual MIME type of the 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 does not exist: {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(
    # The API Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: api_key = "sk-xxx",
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        # "language": "zh", # Optional. If you know the language of the audio, you can use this parameter to specify the language to recognize, to improve recognition accuracy
        "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 {
    // Replace with the actual audio file path
    private static final String AUDIO_FILE = "{YOUR_AUDIO_FILE}";
    // Replace with the actual MIME type of the audio file
    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"); // Optional. If you know the language of the audio, you can use this parameter to specify the language to recognize, to improve recognition accuracy
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
                // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: .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 {
            // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
            Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException | IOException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }

    // Generate the 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

# The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# Replace ABSOLUTE_PATH/{YOUR_AUDIO_FILE} with the absolute path of your local audio file
audio_file_path = "file://ABSOLUTE_PATH/{YOUR_AUDIO_FILE}"

messages = [
    {"role": "user", "content": [{"audio": audio_file_path}]}
]
response = dashscope.MultiModalConversation.call(
    # The API Key differs between the Singapore/US regions and the Beijing region. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
    # If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: api_key = "sk-xxx"
    api_key=os.getenv("DASHSCOPE_API_KEY"),
    model="qwen3-asr-flash",
    messages=messages,
    result_format="message",
    asr_options={
        # "language": "zh", # Optional. If you know the language of the audio, you can use this parameter to specify the language to recognize, to improve recognition accuracy
        "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 {
        // Replace ABSOLUTE_PATH/{YOUR_AUDIO_FILE} with the absolute path of your local 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"); // Optional. If you know the language of the audio, you can use this parameter to specify the language to recognize, to improve recognition accuracy
        MultiModalConversationParam param = MultiModalConversationParam.builder()
                // The API Key differs between the Singapore and Beijing regions. Get an API Key: https://www.alibabacloud.com/help/model-studio/get-api-key
                // If you have not configured the environment variable, replace the following line with your Alibaba Cloud Model Studio API Key: .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 {
            // The following is the configuration for the Singapore region. When calling, replace "{WorkspaceId}" with your actual workspace ID. The configuration differs by region.
            Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
            simpleMultiModalConversationCall();
        } catch (ApiException | NoApiKeyException | UploadFileException e) {
            System.out.println(e.getMessage());
        }
        System.exit(0);
    }
}