非即時語音辨識

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

# 以下為新加坡地區的配置，調用時請將"{WorkspaceId}"替換為真實的業務空間ID，各地區的配置不同。
dashscope.base_http_api_url = 'https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1'

# 新加坡地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
# 若沒有配置環境變數，請用阿里雲百鍊API Key將下行替換為：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為選擇性參數，用於指定待識別音訊語言代碼。取值範圍請參見API參考文檔。
)

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) {
        // 以下為新加坡地區的配置，調用時請將"{WorkspaceId}"替換為真實的業務空間ID，各地區的配置不同。
        Constants.baseHttpApiUrl = "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/api/v1";
        // 建立轉寫請求參數。
        TranscriptionParam param =
                TranscriptionParam.builder()
                        // 新加坡和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
                        // 若沒有配置環境變數，請用阿里雲百鍊API Key將下行替換為：.apiKey("sk-xxx")
                        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
                        .model("qwen-audio-3.0-asr-flash-filetrans")
                        // language_hints為選擇性參數，用於指定待識別音訊語言代碼。取值範圍請參見API參考文檔。
                        .parameter("language_hints", new String[]{"zh", "en"})
                        .fileUrls(
                                Arrays.asList(
                                        "{YOUR_AUDIO_URL}"))
                        .build();
        try {
            Transcription transcription = new Transcription();
            // 提交轉寫請求
            TranscriptionResult result = transcription.asyncCall(param);
            System.out.println("RequestId: " + result.getRequestId());
            // 檢查任務是否提交成功
            if (result.getTaskId() == null) {
                System.out.println("Error: " + result.getOutput());
                System.exit(1);
            }
            // 阻塞等待任務完成並擷取結果
            result = transcription.wait(
                    TranscriptionQueryParam.FromTranscriptionParam(param, result.getTaskId()));
            // 擷取轉寫結果
            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);
    }
}

// 運行前的準備工作:
// Windows/Mac/Linux 通用:
// 1. 確保已安裝 Node.js (建議版本 >= 14)
// 2. 運行以下命令安裝必要的依賴: npm install openai

import OpenAI from "openai";

const client = new OpenAI({
  // 新加坡/美國地區和北京地區的API Key不同。擷取API Key：https://www.alibabacloud.com/help/zh/model-studio/get-api-key
  // 若沒有配置環境變數，請用阿里雲百鍊API Key將下行替換為：apiKey: "sk-xxx",
  apiKey: process.env.DASHSCOPE_API_KEY,
  // 以下為新加坡地區的配置，調用時請將"{WorkspaceId}"替換為真實的業務空間ID，各地區的配置不同。
  baseURL: "https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1",
});

async function main() {
  try {
    const streamEnabled = false; // 是否開啟流式輸出
    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設為False時，不能設定stream_options參數
      // stream_options: {
      //   "include_usage": true
      // },
      asr_options: {
        // language: "zh",
        enable_itn: false
      }
    });

    if (streamEnabled) {
      let fullContent = "";
      console.log("流式輸出內容為：");
      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(`完整內容為：${fullContent}`);
    } else {
      console.log(`非流式輸出內容為：${completion.choices[0].message.content}`);
    }
  } catch (err) {
    console.error(`錯誤資訊：${err}`);
  }
}

main();