Pierwsze kroki z interfejsem Gemini Live API za pomocą Firebase AI Logic

import FirebaseAILogic

// Initialize the Gemini Developer API backend service.
// Create a `liveModel` instance with a model that supports the Live API.
let liveModel = FirebaseAI.firebaseAI(backend: .googleAI()).liveModel(
  modelName: "GEMINI_LIVE_API_MODEL_NAME",
  // Configure the model to respond with audio.
  generationConfig: LiveGenerationConfig(
    responseModalities: [.audio]
  )
)

do {
  let session = try await liveModel.connect()

  // Load the audio file, or tap a microphone.
  guard let audioFile = NSDataAsset(name: "audio.pcm") else {
    fatalError("Failed to load audio file")
  }

  // Provide the audio data.
  await session.sendAudioRealtime(audioFile.data)

  var outputText = ""
  for try await message in session.responses {
    if case let .content(content) = message.payload {
      content.modelTurn?.parts.forEach { part in
        if let part = part as? InlineDataPart, part.mimeType.starts(with: "audio/pcm") {
          // Handle 16bit pcm audio data at 24khz
          playAudio(part.data)
        }
      }
      // Optional: if you don't need to send more requests.
      if content.isTurnComplete {
        await session.close()
      }
    }
  }
} catch {
  fatalError(error.localizedDescription)
}

// Initialize the Gemini Developer API backend service.
// Create a `liveModel` instance with a model that supports the Live API.
val liveModel = Firebase.ai(backend = GenerativeBackend.googleAI()).liveModel(
    modelName = "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to respond with audio.
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.AUDIO
   }
)

val session = liveModel.connect()

// This is the recommended approach.
// However, you can create your own recorder and handle the stream.
session.startAudioConversation()

ExecutorService executor = Executors.newFixedThreadPool(1);
// Initialize the Gemini Developer API backend service.
// Create a `liveModel` instance with a model that supports the Live API.
LiveGenerativeModel lm = FirebaseAI.getInstance(GenerativeBackend.googleAI()).liveModel(
        "GEMINI_LIVE_API_MODEL_NAME",
        // Configure the model to respond with audio.
        new LiveGenerationConfig.Builder()
                .setResponseModality(ResponseModality.AUDIO)
                .build()
);
LiveModelFutures liveModel = LiveModelFutures.from(lm);

ListenableFuture<LiveSession> sessionFuture =  liveModel.connect();

Futures.addCallback(sessionFuture, new FutureCallback<LiveSession>() {
    @Override
    public void onSuccess(LiveSession ses) {
	 LiveSessionFutures session = LiveSessionFutures.from(ses);
        session.startAudioConversation();
    }
    @Override
    public void onFailure(Throwable t) {
        // Handle exceptions
    }
}, executor);

import { initializeApp } from "firebase/app";
import { getAI, getLiveGenerativeModel, GoogleAIBackend, ResponseModality } from "firebase/ai";

// TODO(developer): Replace the following with your app's Firebase configuration
// See: https://firebase.google.com/docs/web/learn-more#config-object
const firebaseConfig = {
  // ...
};

// Initialize FirebaseApp
const firebaseApp = initializeApp(firebaseConfig);

// Initialize the Gemini Developer API backend service.
const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

// Create a `LiveGenerativeModel` instance with a model that supports the Live API.
const liveModel = getLiveGenerativeModel(ai, {
  model: "GEMINI_LIVE_API_MODEL_NAME",
  // Configure the model to respond with audio.
  generationConfig: {
    responseModalities: [ResponseModality.AUDIO],
  },
});

const session = await liveModel.connect();

// Start the audio conversation.
const audioConversationController = await startAudioConversation(session);

// ... Later, to stop the audio conversation
// await audioConversationController.stop()

import 'package:firebase_ai/firebase_ai.dart';
import 'package:firebase_core/firebase_core.dart';
import 'firebase_options.dart';
import 'package:your_audio_recorder_package/your_audio_recorder_package.dart';

late LiveSession _session;
final _audioRecorder = YourAudioRecorder();

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

// Initialize the Gemini Developer API backend service.
// Create a `liveGenerativeModel` instance with a model that supports the Live API.
final liveModel = FirebaseAI.googleAI().liveGenerativeModel(
  model: 'GEMINI_LIVE_API_MODEL_NAME',
  // Configure the model to respond with audio.
  liveGenerationConfig: LiveGenerationConfig(
    responseModalities: [ResponseModalities.audio],
  ),
);

_session = await liveModel.connect();

final audioRecordStream = _audioRecorder.startRecordingStream();
// Map the Uint8List stream to InlineDataPart stream.
final mediaChunkStream = audioRecordStream.map((data) {
  return InlineDataPart('audio/pcm', data);
});
await for (final chunk in mediaChunkStream) {
  await _session.sendAudioRealtime(chunk);
}

// In a separate thread, receive the audio response from the model.
await for (final message in _session.receive()) {
   // Process the received message.
}

using Firebase;
using Firebase.AI;

async Task SendTextReceiveAudio() {
  // Initialize the Gemini Developer API backend service.
  // Create a `LiveModel` instance with a model that supports the Live API.
  var liveModel = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetLiveModel(
      modelName: "GEMINI_LIVE_API_MODEL_NAME",
      // Configure the model to respond with audio.
      liveGenerationConfig: new LiveGenerationConfig(
          responseModalities: new[] { ResponseModality.Audio })
    );

  LiveSession session = await liveModel.ConnectAsync();

  // Start a coroutine to send audio from the Microphone.
  var recordingCoroutine = StartCoroutine(SendAudio(session));

  // Start receiving the response.
  await ReceiveAudio(session);
}

IEnumerator SendAudio(LiveSession liveSession) {
  string microphoneDeviceName = null;
  int recordingFrequency = 16000;
  int recordingBufferSeconds = 2;

  var recordingClip = Microphone.Start(microphoneDeviceName, true,
                                       recordingBufferSeconds, recordingFrequency);

  int lastSamplePosition = 0;
  while (true) {
    if (!Microphone.IsRecording(microphoneDeviceName)) {
      yield break;
    }

    int currentSamplePosition = Microphone.GetPosition(microphoneDeviceName);

    if (currentSamplePosition != lastSamplePosition) {
      // The Microphone uses a circular buffer, so we need to check if the
      // current position wrapped around to the beginning, and handle it accordingly.
      int sampleCount;
      if (currentSamplePosition > lastSamplePosition) {
        sampleCount = currentSamplePosition - lastSamplePosition;
      } else {
        sampleCount = recordingClip.samples - lastSamplePosition + currentSamplePosition;
      }

      if (sampleCount > 0) {
        // Get the audio chunk.
        float[] samples = new float[sampleCount];
        recordingClip.GetData(samples, lastSamplePosition);

        // Send the data, discarding the resulting Task to avoid the warning.
        _ = liveSession.SendAudioAsync(samples);

        lastSamplePosition = currentSamplePosition;
      }
    }

    // Wait for a short delay before reading the next sample from the Microphone.
    const float MicrophoneReadDelay = 0.5f;
    yield return new WaitForSeconds(MicrophoneReadDelay);
  }
}

Queue<float> audioBuffer = new();

async Task ReceiveAudio(LiveSession liveSession) {
  int sampleRate = 24000;
  int channelCount = 1;

  // Create a looping AudioClip to fill with the received audio data.
  int bufferSamples = (int)(sampleRate * channelCount);
  AudioClip clip = AudioClip.Create("StreamingPCM", bufferSamples, channelCount,
                                    sampleRate, true, OnAudioRead);

  // Attach the clip to an AudioSource and start playing it.
  AudioSource audioSource = GetComponent<AudioSource>();
  audioSource.clip = clip;
  audioSource.loop = true;
  audioSource.Play();

  // Start receiving the response.
  await foreach (var message in liveSession.ReceiveAsync()) {
    // Process the received message
    foreach (float[] pcmData in message.AudioAsFloat) {
      lock (audioBuffer) {
        foreach (float sample in pcmData) {
          audioBuffer.Enqueue(sample);
        }
      }
    }
  }
}

// This method is called by the AudioClip to load audio data.
private void OnAudioRead(float[] data) {
  int samplesToProvide = data.Length;
  int samplesProvided = 0;

  lock(audioBuffer) {
    while (samplesProvided < samplesToProvide && audioBuffer.Count > 0) {
      data[samplesProvided] = audioBuffer.Dequeue();
      samplesProvided++;
    }
  }

  while (samplesProvided < samplesToProvide) {
    data[samplesProvided] = 0.0f;
    samplesProvided++;
  }
}