import com.alibaba.dashscope.audio.omni.*;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.google.gson.JsonObject;
import javax.sound.sampled.*;
import java.util.*;
import java.util.concurrent.atomic.AtomicBoolean;
public class Main {
private static final int INPUT_CHUNK_SIZE = 3200;
private static final int OUTPUT_CHUNK_SIZE = 4800;
private static final AtomicBoolean running = new AtomicBoolean(true);
private static SourceDataLine speaker;
public static void main(String[] args) throws InterruptedException {
String apiKey = System.getenv("DASHSCOPE_API_KEY");
if (apiKey == null || apiKey.isEmpty()) {
System.err.println("请设置环境变量 DASHSCOPE_API_KEY");
System.exit(1);
}
OmniRealtimeParam param = OmniRealtimeParam.builder()
.model("qwen3.5-livetranslate-flash-realtime")
.url("wss://dashscope.aliyuncs.com/api-ws/v1/realtime")
.apikey(apiKey)
.build();
OmniRealtimeCallback callback = new OmniRealtimeCallback() {
@Override
public void onOpen() {
System.out.println("[连接已建立]");
}
@Override
public void onEvent(JsonObject message) {
String type = message.get("type").getAsString();
switch (type) {
case "input_audio_buffer.speech_started":
System.out.println("====== 检测到语音输入 ======");
break;
case "input_audio_buffer.speech_stopped":
System.out.println("====== 语音输入结束 ======");
break;
case "conversation.item.input_audio_transcription.completed":
String originalText = message.get("transcript").getAsString();
System.out.println("[原文] " + originalText);
break;
case "response.audio_transcript.done":
String translatedText = message.get("transcript").getAsString();
System.out.println("[翻译结果] " + translatedText);
break;
case "response.audio.delta":
String audioB64 = message.get("delta").getAsString();
byte[] audioBytes = Base64.getDecoder().decode(audioB64);
if (speaker != null) {
speaker.write(audioBytes, 0, audioBytes.length);
}
break;
case "error":
JsonObject error = message.get("error").getAsJsonObject();
System.err.println("[错误] " + error.get("message").getAsString());
break;
}
}
@Override
public void onClose(int code, String reason) {
System.out.println("[连接已关闭] code: " + code + ", reason: " + reason);
}
};
OmniRealtimeConversation conversation = new OmniRealtimeConversation(param, callback);
try {
AudioFormat speakerFormat = new AudioFormat(24000, 16, 1, true, false);
DataLine.Info speakerInfo = new DataLine.Info(SourceDataLine.class, speakerFormat);
speaker = (SourceDataLine) AudioSystem.getLine(speakerInfo);
speaker.open(speakerFormat, OUTPUT_CHUNK_SIZE * 4);
speaker.start();
AudioFormat micFormat = new AudioFormat(16000, 16, 1, true, false);
DataLine.Info micInfo = new DataLine.Info(TargetDataLine.class, micFormat);
if (!AudioSystem.isLineSupported(micInfo)) {
System.err.println("麦克风不可用");
System.exit(1);
}
TargetDataLine microphone = (TargetDataLine) AudioSystem.getLine(micInfo);
microphone.open(micFormat);
microphone.start();
conversation.connect();
Map<String, Object> phrases = new HashMap<>();
phrases.put("人工智能", "Artificial Intelligence");
phrases.put("机器学习", "Machine Learning");
OmniRealtimeConfig config = OmniRealtimeConfig.builder()
.modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
.voice("Tina")
.inputAudioFormat(OmniRealtimeAudioFormat.PCM_16000HZ_MONO_16BIT)
.outputAudioFormat(OmniRealtimeAudioFormat.PCM_24000HZ_MONO_16BIT)
.InputAudioTranscription("qwen3-asr-flash-realtime")
.translationConfig(OmniRealtimeTranslationParam.builder()
.language("en")
.corpus(OmniRealtimeTranslationParam.Corpus.builder()
.phrases(phrases)
.build())
.build())
.build();
conversation.updateSession(config);
Runtime.getRuntime().addShutdownHook(new Thread(() -> {
System.out.println("\n[正在退出...]");
running.set(false);
microphone.stop();
microphone.close();
speaker.stop();
speaker.close();
try {
conversation.endSession();
} catch (InterruptedException e) {
Thread.currentThread().interrupt();
}
conversation.close(1000, "用户停止");
}));
System.out.println("[开始实时翻译] 请对着麦克风说话，按 Ctrl+C 退出");
byte[] buffer = new byte[INPUT_CHUNK_SIZE];
while (running.get()) {
int bytesRead = microphone.read(buffer, 0, buffer.length);
if (bytesRead > 0) {
conversation.appendAudio(Base64.getEncoder().encodeToString(buffer));
}
}
} catch (NoApiKeyException e) {
System.err.println("API Key 错误: " + e.getMessage());
} catch (Exception e) {
System.err.println("发生异常: " + e.getMessage());
e.printStackTrace();
}
}
}
