Non-real-time speech recognition

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

# 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'

# The API Key differs between the Singapore and Beijing regions. Get an API Key: https://www.alibabacloud.com/help/zh/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: dashscope.api_key = "sk-xxx"
dashscope.api_key = os.getenv("DASHSCOPE_API_KEY")

task_response = Transcription.async_call(
    model='qwen-audio-3.0-asr-flash-filetrans',
    file_urls=['{YOUR_AUDIO_URL}'],
    language_hints=['zh', 'en']  # language_hints is an optional parameter used to specify the language codes of the audio to be recognized. For the value range, see the API reference documentation.
)

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)

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) {
        // 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";
        // Create the transcription request parameters.
        TranscriptionParam param =
                TranscriptionParam.builder()
                        // The API Key differs between the Singapore and Beijing regions. Get an API Key: https://help.aliyun.com/zh/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("qwen-audio-3.0-asr-flash-filetrans")
                        // language_hints is an optional parameter used to specify the language codes of the audio to be recognized. For the value range, see the API reference documentation.
                        .parameter("language_hints", new String[]{"zh", "en"})
                        .fileUrls(
                                Arrays.asList(
                                        "{YOUR_AUDIO_URL}"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // Submit the transcription request
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // Check whether the task was submitted successfully
            if (result.getTaskId() == null) {
                System.out.println("Error: " + result.getOutput());
                System.exit(1);
            }
            // Block and wait for the task to complete and get the result
            result = transcription.wait(
                    TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            // Get the transcription result
            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);
    }
}

// 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";

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/zh/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",
});

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: "{YOUR_AUDIO_URL}"
              }
            }
          ]
        }
      ],
      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();