使用 Gemini Live API 进行双向流式传输

// Initialize the Vertex AI service and create a `LiveModel` instance
val model = Firebase.vertexAI.liveModel(
    // The Live API requires this specific model.
    modelName = "gemini-2.0-flash-live-preview-04-09",
    // Configure the model to respond with text
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.TEXT 
   }
)

val session = model.connect()

// Provide a text prompt
val audioContent = content("user") { audioData }

session.send(audioContent)

var outputText = ""
session.receive().collect {
    if(it.status == Status.TURN_COMPLETE) {
        // Optional: if you don't require to send more requests.
        session.stopReceiving();
    }
    outputText = outputText + it.text
}

// Output received from the server.
println(outputText)

TODO - snippet ExecutorService executor = Executors.newFixedThreadPool(1);
// Initialize the Vertex AI service and create a `LiveModel` instance
LiveGenerativeModel lm = FirebaseVertexAI.getInstance().liveModel(
        // The Live API requires this specific model.
        "gemini-2.0-flash-live-preview-04-09",
        // Configure the model to respond with text
        new LiveGenerationConfig.Builder()
                .setResponseModalities(ResponseModality.TEXT)
                .build()
);
LiveModelFutures model = LiveModelFutures.from(lm);
ListenableFuture<LiveSession> sessionFuture =  model.connect();
class LiveContentResponseSubscriber implements Subscriber<LiveContentResponse> {
    @Override
    public void onSubscribe(Subscription s) {
        s.request(Long.MAX_VALUE); // Request an unlimited number of items
    }
    @Override
    public void onNext(LiveContentResponse liveContentResponse) {
        // Handle the response from the server.
	System.out.println(liveContentResponse.getText());
    }
    @Override
    public void onError(Throwable t) {
        System.err.println("Error: " + t.getMessage());
    }
    @Override
    public void onComplete() {
        System.out.println("Done receiving messages!");
    }
}
Futures.addCallback(sessionFuture, new FutureCallback<LiveSession>() {
    @Override
    public void onSuccess(LiveSession ses) {
	 LiveSessionFutures session = LiveSessionFutures.from(ses);
        // Send Audio data
	 session.send(new Content.Builder().addInlineData(audioData, "audio/pcm").build());

        session.send(text);
        Publisher<LiveContentResponse> publisher = session.receive();
        publisher.subscribe(new LiveContentResponseSubscriber());
    }
    @Override
    public void onFailure(Throwable t) {
        // Handle exceptions
    }
}, executor);

import 'package:firebase_vertexai/firebase_vertexai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';
import 'package:your_audio_recorder_package/your_audio_recorder_package.dart';
import 'dart:async';

late LiveModelSession _session;
final _audioRecorder = YourAudioRecorder();

await Firebase.initializeApp(
  options: DefaultFirebaseOptions.currentPlatform,
);

final model = FirebaseVertexAI.instance.liveModel(
  model: 'gemini-2.0-flash-live-preview-04-09',
  config: LiveGenerationConfig(responseModality: ResponseModality.text),
);

_session = await model.connect();

final audioRecordStream = _audioRecorder.startRecordingStream();
final mediaChunkStream = audioRecordStream.map((data) {
  return InlineDataPart('audio/pcm', data);
});

await _session.startMediaStream(mediaChunkStream);

final responseStream = _session.receive();

return responseStream.asyncMap((response) async {
  if (response.parts.isNotEmpty && response.parts.first.text != null) {
    return response.parts.first.text!;
  } else {
    throw Exception('Text response not found.');
  }
});

Future main() async {
  try {
    final textStream = await audioToText();

    await for (final text in textStream) {
      print('Received text: $text');
      // Handle the text response
    }
  } catch (e) {
    print('Error: $e');
  }
}

// Initialize the Vertex AI service and create a `LiveModel` instance
val model = Firebase.vertexAI.liveModel(
    // The Live API requires this specific model.
    modelName = "gemini-2.0-flash-live-preview-04-09",
    // Configure the model to respond with text
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.AUDIO
   }
)

val session = model.connect()

// Provide a text prompt
val text = "tell a short story"

session.send(text)

session.receive().collect {
    if(it.status == Status.TURN_COMPLETE) {
        // Optional: if you don't require to send more requests.
        session.stopReceiving();
    }
    // Handle 16bit pcm audio data at 24khz
    playAudio(it.data)
}

ExecutorService executor = Executors.newFixedThreadPool(1);
// Initialize the Vertex AI service and create a `LiveModel` instance
LiveGenerativeModel lm = FirebaseVertexAI.getInstance().liveModel(
        // The Live API requires this specific model.
        "gemini-2.0-flash-live-preview-04-09",
        // Configure the model to respond with text
        new LiveGenerationConfig.Builder()
                .setResponseModalities(ResponseModality.AUDIO)
                .build()
);
LiveModelFutures model = LiveModelFutures.from(lm);
ListenableFuture<LiveSession> sessionFuture =  model.connect();
class LiveContentResponseSubscriber implements Subscriber<LiveContentResponse> {
    @Override
    public void onSubscribe(Subscription s) {
        s.request(Long.MAX_VALUE); // Request an unlimited number of items
    }
    @Override
    public void onNext(LiveContentResponse liveContentResponse) {
        // Handle 16bit pcm audio data at 24khz
	liveContentResponse.getData();
    }
    @Override
    public void onError(Throwable t) {
        System.err.println("Error: " + t.getMessage());
    }
    @Override
    public void onComplete() {
        System.out.println("Done receiving messages!");
    }
}
Futures.addCallback(sessionFuture, new FutureCallback<LiveSession>() {
    @Override
    public void onSuccess(LiveSession ses) {
	 LiveSessionFutures session = LiveSessionFutures.from(ses);
        // Provide a text prompt
        String text = "tell me a short story?";
        session.send(text);
        Publisher<LiveContentResponse> publisher = session.receive();
        publisher.subscribe(new LiveContentResponseSubscriber());
    }
    @Override
    public void onFailure(Throwable t) {
        // Handle exceptions
    }
}, executor);

import 'package:firebase_vertexai/firebase_vertexai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';
import 'dart:async';
import 'dart:typed_data';

late LiveModelSession _session;

Future<Stream<Uint8List>> textToAudio(String textPrompt) async {
  WidgetsFlutterBinding.ensureInitialized();

  await Firebase.initializeApp(
    options: DefaultFirebaseOptions.currentPlatform,
  );

  final model = FirebaseVertexAI.instance.liveModel(
    model: 'gemini-2.0-flash-live-preview-04-09',
    config: LiveGenerationConfig(responseModality: ResponseModality.audio),
  );

  _session = await model.connect();

  final prompt = Content.text(textPrompt);

  await _session.send(input: prompt);

  return _session.receive().asyncMap((response) async {
    if (response is LiveServerContent && response.modelTurn?.parts != null) {
       for (final part in response.modelTurn!.parts) {
         if (part is InlineDataPart) {
           return part.bytes;
         }
       }
    }
    throw Exception('Audio data not found');
  });
}

Future<void> main() async {
  try {
    final audioStream = await textToAudio('Convert this text to audio.');

    await for (final audioData in audioStream) {
      // Process the audio data (e.g., play it using an audio player package)
      print('Received audio data: ${audioData.length} bytes');
      // Example using flutter_sound (replace with your chosen package):
      // await _flutterSoundPlayer.startPlayer(fromDataBuffer: audioData);
    }
  } catch (e) {
    print('Error: $e');
  }
}