LiveTranslate Java SDK

User guide: For tutorials and complete examples, see Real-time translation.

Before you begin

Install the DashScope SDK. Make sure that your DashScope SDK version is 2.22.5 or later.
Obtain an API key.

Configuration overview

Three builder objects control a translation session:

OmniRealtimeParam          --> Connection: model, endpoint, API key
  +-- OmniRealtimeConfig   --> Session: audio formats, voice, modalities
       +-- OmniRealtimeTranslationParam  --> Translation: target language, custom terminology

Pass OmniRealtimeParam to the constructor. After connecting, call updateSession() with OmniRealtimeConfig to set audio and translation options. Defaults apply if you skip updateSession().

Quick start

Connect, send audio, and receive translated text:

import com.alibaba.dashscope.audio.omni.*;
import com.alibaba.dashscope.exception.NoApiKeyException;
import com.google.gson.JsonObject;
import java.util.Arrays;

// 1. Build connection parameters
OmniRealtimeParam param = OmniRealtimeParam.builder()
  .model("qwen3.5-livetranslate-flash-realtime")
  .url("wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime")
  .apikey(System.getenv("DASHSCOPE_API_KEY"))
  .build();

// 2. Define a callback to handle server events
OmniRealtimeCallback callback = new OmniRealtimeCallback() {
  @Override public void onOpen() { System.out.println("Connected"); }
  @Override
  public void onEvent(JsonObject message) {
    String type = message.get("type").getAsString();
    if ("response.audio_transcript.done".equals(type)) {
      System.out.println("Translation: " + message.get("transcript").getAsString());
    }
  }
  @Override
  public void onClose(int code, String reason) {
    System.out.println("Closed: " + code + " " + reason);
  }
};

// 3. Open a session and start streaming audio
OmniRealtimeConversation conversation = new OmniRealtimeConversation(param, callback);
conversation.connect();

// 4. Configure translation target language
OmniRealtimeConfig config = OmniRealtimeConfig.builder()
  .modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
  .translationConfig(OmniRealtimeTranslationParam.builder()
    .language("en")
    .build())
  .build();
conversation.updateSession(config);

// 5. Send Base64-encoded audio chunks (PCM 16 kHz, 16-bit, mono)
conversation.appendAudio(audioBase64);

// 6. End the session when done
conversation.endSession();

Request parameters

OmniRealtimeParam

Build connection parameters with OmniRealtimeParam.builder().

Sample code

OmniRealtimeParam param = OmniRealtimeParam.builder()
  .model("qwen3.5-livetranslate-flash-realtime")
  .url("wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime")
  // If no environment variable is set, replace the next line with your API key: .apikey("YOUR_API_KEY")
  .apikey(System.getenv("DASHSCOPE_API_KEY"))
  .build();

Parameter	Type	Required	Description
`model`	`String`	Yes	Model name. We recommend `qwen3.5-livetranslate-flash-realtime`. `qwen3-livetranslate-flash-realtime` is the legacy model.
`url`	`String`	Yes	WebSocket endpoint. Use `wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime`.
`apikey`	`String`	No	API key. Defaults to the `DASHSCOPE_API_KEY` environment variable.

OmniRealtimeConfig

Build session parameters with OmniRealtimeConfig.builder(), then call conversation.updateSession(config).

Sample code

// Set custom translation phrases
Map<String, Object> phrases = new HashMap<>();
phrases.put("Inteligencia Artificial", "Artificial Intelligence");
phrases.put("Aprendizaje Automático", "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);

Parameter	Type	Required	Description
`modalities`	`List<OmniRealtimeModality>`	No	Output modalities. Default: `[AUDIO, TEXT]`. Set `[TEXT]` for text only.
`voice`	`String`	No	Voice for synthesized speech. Default: `Tina` for Qwen3.5-LiveTranslate-Flash-Realtime, or `Cherry` for Qwen3-LiveTranslate-Flash-Realtime. See supported voices.
`inputAudioFormat`	`OmniRealtimeAudioFormat`	No	Input audio format. Default: `PCM_16000HZ_MONO_16BIT`.
`outputAudioFormat`	`OmniRealtimeAudioFormat`	No	Output audio format. Default: `PCM_24000HZ_MONO_16BIT`.
`InputAudioTranscription`	`String`	No	ASR model for transcribing input speech. Set to `qwen3-asr-flash-realtime` to receive source-language transcription with translation.
`translationConfig`	`OmniRealtimeTranslationParam`	No	Translation settings. See OmniRealtimeTranslationParam below.
`enableTurnDetection`	`boolean`	No	Whether to enable VAD (Voice Activity Detection). Default value: `true`, which enables VAD mode where the server automatically detects speech start/end and triggers translation. Set to `false` to switch to Manual mode, where the client manually submits audio via the `commit()` method. For detailed parameter descriptions, see the `turn_detection` description in the Client events document.

OmniRealtimeTranslationParam

Build translation parameters with OmniRealtimeTranslationParam.builder().

Sample code

// Set translation phrases
Map<String, Object> phrases = new HashMap<>();
phrases.put("Inteligencia Artificial", "Artificial Intelligence");  // Source language word: Target language translation
phrases.put("Aprendizaje Automático", "Machine Learning");

OmniRealtimeTranslationParam translationParam = OmniRealtimeTranslationParam.builder()
  .language("en")  // Target language code
  .corpus(OmniRealtimeTranslationParam.Corpus.builder()
    .phrases(phrases)
    .build())
  .build();

Parameter	Type	Required	Description
`language`	`String`	No	Target language code. Default: `en`. See supported languages.
`corpus`	`Corpus`	No	Custom terminology for domain-specific terms.
`corpus.phrases`	`Map<String, Object>`	No	Term mappings. Keys: source terms; values: target translations. Example: `{"Inteligencia Artificial": "Artificial Intelligence"}`

Key interfaces

OmniRealtimeConversation

Manages the WebSocket connection and audio streaming. Import: com.alibaba.dashscope.audio.omni.OmniRealtimeConversation

Method	Description
`OmniRealtimeConversation(OmniRealtimeParam param, OmniRealtimeCallback callback)`	Creates a conversation with connection parameters and an event callback.
`void connect()`	Opens the WebSocket connection. Triggers session.created and session.updated. Throws `NoApiKeyException`, `InterruptedException`.
`void updateSession(OmniRealtimeConfig config)`	Updates session configuration. Triggers session.updated. Omitted parameters use defaults.
`void appendAudio(String audioBase64)`	Sends a Base64-encoded audio chunk. The server detects speech boundaries and triggers translation automatically.
`void commit()`	In Manual mode, commits audio previously appended to the server buffer via the `appendAudio` method. The server automatically begins generating a translation response upon receiving the commit. In VAD mode, this method does not need to be called as the server commits automatically. Triggers input_audio_buffer.committed event.
`void clearAppendedAudio()`	Clears uncommitted audio data from the server buffer. Triggers input_audio_buffer.cleared event.
`void endSession()`	Ends the session. The server finishes in-progress translations before sending session.finished. Throws `InterruptedException`.
`void close(int code, String reason)`	Stops the task and closes the WebSocket connection.
`String getSessionId()`	Returns the session ID.
`String getResponseId()`	Returns the response ID of the latest server response.
`long getFirstTextDelay()`	Returns the first text delay of the latest response in milliseconds.
`long getFirstAudioDelay()`	Returns the first audio delay of the latest response in milliseconds.

OmniRealtimeCallback

Handles server events over WebSocket. Extend this class and implement each method. Import: com.alibaba.dashscope.audio.omni.OmniRealtimeCallback

Method	Parameters	Description
`void onOpen()`	None	Called when the WebSocket connection opens.
`abstract void onEvent(JsonObject message)`	`message`: A JSON object containing a server event.	Called for each server event. Parse the `type` field to identify the event.
`abstract void onClose(int code, String reason)`	`code`: WebSocket status code. `reason`: Closure description.	Called when the WebSocket closes.

Common event types in onEvent:

Event type	Description
`input_audio_buffer.speech_started`	Speech detected in the audio stream.
`input_audio_buffer.speech_stopped`	End of a speech segment detected.
`conversation.item.input_audio_transcription.completed`	Source-language transcription ready. Read `message.get("transcript")`. Requires `InputAudioTranscription`.
`response.audio_transcript.done`	Translated text ready. Read `message.get("transcript")`.
`response.audio.delta`	Translated audio chunk available. Read `message.get("delta")` for Base64-encoded audio.
`error`	An error occurred. Read `message.get("error").getAsJsonObject().get("message")` for details.

Complete example

This example records microphone audio and translates it in real time.

Sample code for real-time translation from a microphone

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("Set the DASHSCOPE_API_KEY environment variable.");
      System.exit(1);
    }

    OmniRealtimeParam param = OmniRealtimeParam.builder()
      .model("qwen3.5-livetranslate-flash-realtime")
      .url("wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime")
      .apikey(apiKey)
      .build();

    OmniRealtimeCallback callback = new OmniRealtimeCallback() {
      @Override
      public void onOpen() {
        System.out.println("[Connection established]");
      }

      @Override
      public void onEvent(JsonObject message) {
        String type = message.get("type").getAsString();
        switch (type) {
          case "input_audio_buffer.speech_started":
            System.out.println("====== Speech input detected ======");
            break;
          case "input_audio_buffer.speech_stopped":
            System.out.println("====== Speech input ended ======");
            break;
          case "conversation.item.input_audio_transcription.completed":
            String originalText = message.get("transcript").getAsString();
            System.out.println("[Original text] " + originalText);
            break;
          case "response.audio_transcript.done":
            String translatedText = message.get("transcript").getAsString();
            System.out.println("[Translation result] " + 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("[Error] " + error.get("message").getAsString());
            break;
        }
      }

      @Override
      public void onClose(int code, String reason) {
        System.out.println("[Connection closed] 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("Microphone is not available.");
        System.exit(1);
      }
      TargetDataLine microphone = (TargetDataLine) AudioSystem.getLine(micInfo);
      microphone.open(micFormat);
      microphone.start();

      conversation.connect();

      Map<String, Object> phrases = new HashMap<>();
      phrases.put("Inteligencia Artificial", "Artificial Intelligence");
      phrases.put("Aprendizaje Automático", "Machine Learning");

      OmniRealtimeConfig config = OmniRealtimeConfig.builder()
        .modalities(Arrays.asList(OmniRealtimeModality.AUDIO, OmniRealtimeModality.TEXT))
        .voice("Cherry")
        .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[Exiting...]");
        running.set(false);
        microphone.stop();
        microphone.close();
        speaker.stop();
        speaker.close();
        try {
          conversation.endSession();
        } catch (InterruptedException e) {
          Thread.currentThread().interrupt();
        }
        conversation.close(1000, "User stopped");
      }));

      System.out.println("[Starting real-time translation] Speak into the microphone. Press Ctrl+C to exit.");

      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 error: " + e.getMessage());
    } catch (Exception e) {
      System.err.println("An exception occurred: " + e.getMessage());
      e.printStackTrace();
    }
  }
}

References

Qwen-LiveTranslate model overview -- Supported languages, voices, and capabilities
Client events -- Client event types and parameters
Server events reference -- Event types, JSON schemas, and error codes
Install the DashScope SDK -- Installation and dependency setup
Get an API key -- API key creation and management

​Before you begin

​Configuration overview

​Quick start

​Request parameters

​OmniRealtimeParam

​OmniRealtimeConfig

​OmniRealtimeTranslationParam

​Key interfaces

​OmniRealtimeConversation

​OmniRealtimeCallback

​Complete example

​References

Before you begin

Configuration overview

Quick start

Request parameters

OmniRealtimeParam

OmniRealtimeConfig

OmniRealtimeTranslationParam

Key interfaces

OmniRealtimeConversation

OmniRealtimeCallback

Complete example

References