语音识别最佳实践

import OpenAI from "openai";

const openai = new OpenAI({
  apiKey: process.env.DASHSCOPE_API_KEY,
  baseURL: "https://dashscope.aliyuncs.com/compatible-mode/v1"
});

const completion = await openai.chat.completions.create({
  model: "qwen3-omni-flash",
  messages: [
    {
      role: "system",
      content: "You are transcribing investment banking discussions. "
             + "Key terms: Bulge Bracket, Boutique, Middle Market, LBO, DCF."
    },
    {
      role: "user",
      content: [
        {
          type: "input_audio",
          input_audio: {
            data: "https://example.com/meeting.mp3",
            format: "mp3"
          }
        },
        { type: "text", text: "Transcribe this audio." }
      ]
    }
  ],
  stream: true,
  modalities: ["text"],
});

for await (const chunk of completion) {
  if (chunk.choices?.[0]?.delta?.content) {
    process.stdout.write(chunk.choices[0].delta.content);
  }
}

curl -X POST https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completions \
-H "Authorization: Bearer $DASHSCOPE_API_KEY" \
-H "Content-Type: application/json" \
-d '{
  "model": "qwen3-omni-flash",
  "messages": [
    {
      "role": "system",
      "content": "You are transcribing investment banking discussions. Key terms: Bulge Bracket, Boutique, Middle Market, LBO, DCF."
    },
    {
      "role": "user",
      "content": [
        {
          "type": "input_audio",
          "input_audio": {
            "data": "https://example.com/meeting.mp3",
            "format": "mp3"
          }
        },
        {
          "type": "text",
          "text": "Transcribe this audio."
        }
      ]
    }
  ],
  "stream": true,
  "modalities": ["text"]
}'

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 java.util.*;

public class ContextEnhancementExample {
  public static void main(String[] args) {
    MultiModalConversation conv = new MultiModalConversation();

    // 系统消息：传入领域上下文
    MultiModalMessage sysMessage = MultiModalMessage.builder()
        .role(Role.SYSTEM.getValue())
        .content(Arrays.asList(
          Collections.singletonMap("text", "Bulge Bracket, Boutique, Middle Market")
        ))
        .build();

    // 用户消息：传入音频
    MultiModalMessage userMessage = MultiModalMessage.builder()
        .role(Role.USER.getValue())
        .content(Arrays.asList(
          Collections.singletonMap("audio",
            "https://example.com/investment-banking-audio.mp3")
        ))
        .build();

    MultiModalConversationParam param = MultiModalConversationParam.builder()
        .apiKey(System.getenv("DASHSCOPE_API_KEY"))
        .model("qwen3-asr-flash")
        .message(sysMessage)
        .message(userMessage)
        .build();

    MultiModalConversationResult result = conv.call(param);
    System.out.println(result.getOutput().getChoices().get(0)
        .getMessage().getContent().get(0).get("text"));
  }
}

import com.alibaba.dashscope.audio.asr.recognition.*;
import com.alibaba.dashscope.audio.asr.vocabulary.*;
import com.alibaba.dashscope.utils.Constants;
import com.google.gson.*;
import java.io.File;

public class HotwordExample {
  public static void main(String[] args) throws Exception {
    String apiKey = System.getenv("DASHSCOPE_API_KEY");
    Constants.baseHttpApiUrl = "https://dashscope.aliyuncs.com/api/v1";
    Constants.baseWebsocketApiUrl = "wss://dashscope.aliyuncs.com/api-ws/v1/inference";

    String targetModel = "fun-asr-realtime";

    // 第 1 步：创建热词列表
    JsonArray vocab = new JsonArray();
    JsonObject word1 = new JsonObject();
    word1.addProperty("text", "Bulge Bracket");
    word1.addProperty("weight", 4);
    vocab.add(word1);

    VocabularyService service = new VocabularyService(apiKey);
    Vocabulary vocabulary = service.createVocabulary(targetModel, "my-app", vocab);

    // 第 2 步：使用热词列表进行识别
    if ("OK".equals(service.queryVocabulary(vocabulary.getVocabularyId()).getStatus())) {
      Recognition recognizer = new Recognition();
      RecognitionParam param = RecognitionParam.builder()
          .model(targetModel)
          .apiKey(apiKey)
          .format("wav")
          .sampleRate(16000)
          .build();
      try {
        System.out.println(recognizer.call(param, new File("audio.wav")));
      } finally {
        recognizer.getDuplexApi().close(1000, "bye");
      }
    }

    service.deleteVocabulary(vocabulary.getVocabularyId());
    System.exit(0);
  }
}