Live API の構成オプション

// ...

let liveModel = FirebaseAI.firebaseAI(backend: .googleAI()).liveModel(
  modelName: "GEMINI_LIVE_API_MODEL_NAME",
  // Configure the model to use a specific voice for its audio response.
  generationConfig: LiveGenerationConfig(
    responseModalities: [.audio],
    speech: SpeechConfig(voiceName: "VOICE_NAME")
  )
)

// ...

// ...

val model = Firebase.ai(backend = GenerativeBackend.googleAI()).liveModel(
    modelName = "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to use a specific voice for its audio response.
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.AUDIO
        speechConfig = SpeechConfig(voice = Voice("VOICE_NAME"))
    }
)

// ...

// ...

LiveGenerativeModel lm = FirebaseAI.getInstance(GenerativeBackend.googleAI()).liveModel(
    "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to use a specific voice for its audio response.
    new LiveGenerationConfig.Builder()
        .setResponseModality(ResponseModality.AUDIO)
        .setSpeechConfig(new SpeechConfig(new Voice("VOICE_NAME")))
        .build()
);

// ...

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

const liveModel = getLiveGenerativeModel(ai, {
  model: "GEMINI_LIVE_API_MODEL_NAME",
  // Configure the model to use a specific voice for its audio response.
  generationConfig: {
    responseModalities: [ResponseModality.AUDIO],
    speechConfig: {
      voiceConfig: {
        prebuiltVoiceConfig: { voiceName: "VOICE_NAME" },
      },
    },
  },
});

// ...

// ...

final _liveModel = FirebaseAI.googleAI().liveGenerativeModel(
  model: 'GEMINI_LIVE_API_MODEL_NAME',
  // Configure the model to use a specific voice for its audio response.
  liveGenerationConfig: LiveGenerationConfig(
    responseModalities: [ResponseModalities.audio],
    speechConfig: SpeechConfig(voiceName: 'VOICE_NAME'),
  ),
);

// ...

// ...

var liveModel = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetLiveModel(
    modelName: "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to use a specific voice for its audio response
    liveGenerationConfig: new LiveGenerationConfig(
        responseModalities: new[] { ResponseModality.Audio },
        speechConfig: SpeechConfig.UsePrebuiltVoice("VOICE_NAME")
    )
);

// ...

// ...

let liveModel = FirebaseAI.firebaseAI(backend: .googleAI()).liveModel(
  modelName: "GEMINI_LIVE_API_MODEL_NAME",
  // Configure the model to return transcriptions of the audio input and output.
  generationConfig: LiveGenerationConfig(
    responseModalities: [.audio],
    inputAudioTranscription: AudioTranscriptionConfig(),
    outputAudioTranscription: AudioTranscriptionConfig()
  )
)

var inputTranscript: String = ""
var outputTranscript: String = ""

do {
  let session = try await liveModel.connect()
  for try await response in session.responses {
    if case let .content(content) = response.payload {
      if let inputText = content.inputAudioTranscription?.text {
        // Handle transcription text of the audio input.
        inputTranscript += inputText
      }

      if let outputText = content.outputAudioTranscription?.text {
        // Handle transcription text of the audio output.
        outputTranscript += outputText
      }

      if content.isTurnComplete {
        // Log the transcripts after the current turn is complete.
        print("Input audio: \(inputTranscript)")
        print("Output audio: \(outputTranscript)")

        // Reset the transcripts for the next turn.
        inputTranscript = ""
        outputTranscript = ""
      }
    }
  }


} catch {
  // Handle error
}

// ...

// ...

val liveModel = Firebase.ai(backend = GenerativeBackend.googleAI()).liveModel(
    modelName = "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to return transcriptions of the audio input and output.
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.AUDIO
        inputAudioTranscription = AudioTranscriptionConfig()
        outputAudioTranscription = AudioTranscriptionConfig()
   }
)

val liveSession = liveModel.connect()

fun handleTranscription(input: Transcription?, output: Transcription?) {
    input?.text?.let { text ->
        // Handle transcription text of the audio input.
        println("Input Transcription: $text")
    }
    output?.text?.let { text ->
        // Handle transcription text of the audio output.
        println("Output Transcription: $text")
    }
}

liveSession.startAudioConversation(null, ::handleTranscription)

// ...

// ...

ExecutorService executor = Executors.newFixedThreadPool(1);

LiveGenerativeModel lm = FirebaseAI.getInstance(GenerativeBackend.googleAI()).liveModel(
    "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to return transcriptions of the audio input and output.
    new LiveGenerationConfig.Builder()
            .setResponseModality(ResponseModality.AUDIO)
            .setInputAudioTranscription(new AudioTranscriptionConfig())
            .setOutputAudioTranscription(new AudioTranscriptionConfig())
            .build()
    );

LiveModelFutures liveModel = LiveModelFutures.from(lm);
ListenableFuture<LiveSessionFutures> sessionFuture = liveModel.connect();

Futures.addCallback(sessionFuture, new FutureCallback<LiveSessionFutures>() {
    @Override
    public void onSuccess(LiveSessionFutures ses) {
        LiveSessionFutures session = ses;
        session.startAudioConversation((Transcription input, Transcription output) -> {
            if (input != null) {
                // Handle transcription text of the audio input.
                System.out.println("Input Transcription: " + input.getText());
            }
            if (output != null) {
                // Handle transcription text of the audio output.
                System.out.println("Output Transcription: " + output.getText());
            }
            return null;
        });
    }

    @Override
    public void onFailure(Throwable t) {
        // Handle exceptions
        t.printStackTrace();
    }
}, executor);

// ...

// ...

const ai = getAI(firebaseApp, { backend: new GoogleAIBackend() });

const liveModel = getLiveGenerativeModel(ai, {
  model: 'GEMINI_LIVE_API_MODEL_NAME',
  // Configure the model to return transcriptions of the audio input and output.
  generationConfig: {
    responseModalities: [ResponseModality.AUDIO],
    inputAudioTranscription: {},
    outputAudioTranscription: {},
  },
});

const liveSession = await liveModel.connect();

liveSession.sendAudioRealtime({ data, mimeType: "audio/pcm" });

const messages = liveSession.receive();
for await (const message of messages) {
  switch (message.type) {
    case 'serverContent':
      if (message.inputTranscription) {
        // Handle transcription text of the audio input.
        console.log(`Input transcription: ${message.inputTranscription.text}`);
      }
      if (message.outputTranscription) {
        // Handle transcription text of the audio output.
        console.log(`Output transcription: ${message.outputTranscription.text}`);
      } else {
      	 // Handle other message types (modelTurn, turnComplete, interruption).
      }
    default:
      // Handle other message types (toolCall, toolCallCancellation).
  }
}

// ...

// ...

final _liveModel = FirebaseAI.googleAI().liveGenerativeModel(
  model: 'GEMINI_LIVE_API_MODEL_NAME',
  // Configure the model to return transcriptions of the audio input and output.
  liveGenerationConfig: LiveGenerationConfig(
    responseModalities: [ResponseModalities.audio],
    inputAudioTranscription: AudioTranscriptionConfig(),
    outputAudioTranscription: AudioTranscriptionConfig(),
  ),
);

final LiveSession _session = await _liveModel.connect();

await for (final response in _session.receive()) {
  if (response.message case LiveServerContent message) {
    if (message.inputTranscription?.text case final inputText?) {
      // Handle transcription text of the audio input.
      print('Input: $inputText');
    }

    if (message.outputTranscription?.text case final outputText?) {
      // Handle transcription text of the audio output.
      print('Output: $outputText');
    }
  }
}

// ...

// ...

var liveModel = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetLiveModel(
    modelName: "GEMINI_LIVE_API_MODEL_NAME",
    // Configure the model to return transcriptions of the audio input and output
    liveGenerationConfig: new LiveGenerationConfig(
        responseModalities: new[] { ResponseModality.Audio },
        inputAudioTranscription: new AudioTranscriptionConfig(),
        outputAudioTranscription: new AudioTranscriptionConfig()
    )
);

try
{
    var session = await liveModel.ConnectAsync();
    var stream = session.ReceiveAsync();
    await foreach (var response in stream) {
        if (response.Message is LiveSessionContent sessionContent) {
            if (!string.IsNullOrEmpty(sessionContent.InputTranscription?.Text)) {
              // handle transcription text of input audio
            }

            if (!string.IsNullOrEmpty(sessionContent.OutputTranscription?.Text)) {
              // handle transcription text of output audio
            }
        }
    }
}
catch (Exception e)
{
    // Handle error
}

// ...

// ...

let liveModel = FirebaseAI.firebaseAI(backend: .googleAI()).liveModel(
  modelName: "GEMINI_LIVE_API_MODEL_NAME",
  generationConfig: LiveGenerationConfig(
    responseModalities: [.audio],
    // Configure voice activity detection (VAD), interruption handling, and turn coverage.
    // IMPORTANT: Example values shown here. Make sure to update for your use case.
    realtimeInputConfig: RealtimeInputConfig(
      automaticActivityDetection: ActivityDetectionConfig(
        startSensitivity: .low,
        endSensitivity: .low,
        prefixPadding: .milliseconds(20),
        silenceDuration: .milliseconds(500)
      ),
      activityHandling: .interrupt,
      turnCoverage: .onlyActivity
    )
  )
)

// ...

val liveModel = Firebase.ai(backend = GenerativeBackend.googleAI()).liveModel(
    modelName = "GEMINI_LIVE_API_MODEL_NAME",
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.AUDIO
        // Configure voice activity detection (VAD), interruption handling, and turn coverage.
        // IMPORTANT: Example values shown here. Make sure to update for your use case.
        realtimeInputConfig = realtimeInputConfig {
            automaticActivityDetection = ActivityDetectionConfig.builder()
                .setStartSensitivity(ActivityDetectionConfig.Sensitivity.LOW)
                .setEndSensitivity(ActivityDetectionConfig.Sensitivity.LOW)
                .setPrefixPaddingMs(20)
                .setSilenceDurationMs(500)
                .build()
            activityHandling = RealtimeInputConfig.ActivityHandling.INTERRUPT
            turnCoverage = RealtimeInputConfig.TurnCoverage.ONLY_ACTIVITY
        }
    }
)

// ...

LiveGenerativeModel lm = FirebaseAI.getInstance(GenerativeBackend.googleAI()).liveModel(
        "GEMINI_LIVE_API_MODEL_NAME",
        new LiveGenerationConfig.Builder()
                .setResponseModality(ResponseModality.AUDIO)
                // Configure voice activity detection (VAD), interruption handling, and turn coverage.
                // IMPORTANT: Example values shown here. Make sure to update for your use case.
                .setRealtimeInputConfig(RealtimeInputConfig.builder()
                        .setAutomaticActivityDetection(ActivityDetectionConfig.builder()
                                .setStartSensitivity(ActivityDetectionConfig.Sensitivity.LOW)
                                .setEndSensitivity(ActivityDetectionConfig.Sensitivity.LOW)
                                .setPrefixPaddingMs(20)
                                .setSilenceDurationMs(500)
                                .build())
                        .setActivityHandling(RealtimeInputConfig.ActivityHandling.INTERRUPT)
                        .setTurnCoverage(RealtimeInputConfig.TurnCoverage.ONLY_ACTIVITY)
                        .build())
                .build()
);

Not yet supported for Web apps - check back soon!

// ...

final _liveModel = FirebaseAI.googleAI().liveGenerativeModel(
  model: 'GEMINI_LIVE_API_MODEL_NAME',
  liveGenerationConfig: LiveGenerationConfig(
    responseModalities: [ResponseModalities.audio],
    // Configure voice activity detection (VAD), interruption handling, and turn coverage.
    // IMPORTANT: Example values shown here. Make sure to update for your use case.
    realtimeInputConfig: RealtimeInputConfig(
      automaticActivityDetection: ActivityDetectionConfig(
        startSensitivity: Sensitivity.low,
        endSensitivity: Sensitivity.low,
        prefixPaddingMS: 20,
        silenceDurationMS: 500,
      ),
      activityHandling: ActivityHandling.interrupt,
      turnCoverage: TurnCoverage.onlyActivity,
    ),
  ),
);

// ...

var liveModel = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetLiveModel(
    modelName: "GEMINI_LIVE_API_MODEL_NAME",
    liveGenerationConfig: new LiveGenerationConfig(
        responseModalities: new[] { ResponseModality.Audio },
        // Configure voice activity detection (VAD), interruption handling, and turn coverage.
        // IMPORTANT: Example values shown here. Make sure to update for your use case.
        realtimeInputConfig: new RealtimeInputConfig(
            automaticActivityDetection: new ActivityDetectionConfig(
                startSensitivity: ActivityDetectionConfig.Sensitivity.Low,
                endSensitivity: ActivityDetectionConfig.Sensitivity.Low,
                prefixPaddingMS: 20,
                silenceDurationMS: 500
            ),
            activityHandling: RealtimeInputConfig.ActivityHandling.Interrupt,
            turnCoverage: RealtimeInputConfig.TurnCoverage.OnlyActivity
        )
    )
);

// ...

let liveModel = FirebaseAI.firebaseAI(backend: .googleAI()).liveModel(
  modelName: "GEMINI_LIVE_API_MODEL_NAME",
  generationConfig: LiveGenerationConfig(
    responseModalities: [.audio],
    // Disable automatic voice activity detection (VAD).
    realtimeInputConfig: RealtimeInputConfig(
      automaticActivityDetection: .disabled()
    )
  )
)

// ...

val liveModel = Firebase.ai(backend = GenerativeBackend.googleAI()).liveModel(
    modelName = "GEMINI_LIVE_API_MODEL_NAME",
    generationConfig = liveGenerationConfig {
        responseModality = ResponseModality.AUDIO
        // Disable automatic voice activity detection (VAD).
        realtimeInputConfig = realtimeInputConfig {
            automaticActivityDetection = ActivityDetectionConfig.disabled()
        }
    }
)

// ...

LiveGenerativeModel lm = FirebaseAI.getInstance(GenerativeBackend.googleAI()).liveModel(
        "GEMINI_LIVE_API_MODEL_NAME",
        new LiveGenerationConfig.Builder()
                .setResponseModality(ResponseModality.AUDIO)
                // Disable automatic voice activity detection (VAD).
                .setRealtimeInputConfig(RealtimeInputConfig.builder()
                        .setAutomaticActivityDetection(ActivityDetectionConfig.disabled())
                        .build())
                .build()
);

Not yet supported for Web apps - check back soon!

// ...

final _liveModel = FirebaseAI.googleAI().liveGenerativeModel(
  model: 'GEMINI_LIVE_API_MODEL_NAME',
  liveGenerationConfig: LiveGenerationConfig(
    responseModalities: [ResponseModalities.audio],
    // Disable automatic voice activity detection (VAD).
    realtimeInputConfig: RealtimeInputConfig(
      automaticActivityDetection: ActivityDetectionConfig.disabled(),
    ),
  ),
);

// ...

var liveModel = FirebaseAI.GetInstance(FirebaseAI.Backend.GoogleAI()).GetLiveModel(
    modelName: "GEMINI_LIVE_API_MODEL_NAME",
    liveGenerationConfig: new LiveGenerationConfig(
        responseModalities: new[] { ResponseModality.Audio },
        // Disable automatic voice activity detection (VAD).
        realtimeInputConfig: new RealtimeInputConfig(
            automaticActivityDetection: ActivityDetectionConfig.Disabled()
        )
    )
);

// If you disable automatic voice activity detection (VAD), you need to manually demarcate user activity.

// Signal the start of user activity (for example, on push-to-talk button press).
await session.sendStartActivityRealtime()

// Stream user audio data while the user speaks.
await session.sendAudioRealtime(audioData)

// Signal the end of user activity (for example, on button release) to trigger model response.
await session.sendStopActivityRealtime()

// If you disable automatic voice activity detection (VAD), you need to manually demarcate user activity.

// Signal the start of user activity (for example, on push-to-talk button press).
session.sendStartActivityRealtime()

// Stream user audio data while the user speaks.
session.sendAudioRealtime(audioData)

// Signal the end of user activity (for example, on button release) to trigger model response.
session.sendStopActivityRealtime()

// If you disable automatic voice activity detection (VAD), you need to manually demarcate user activity.

// Signal the start of user activity (for example, on push-to-talk button press).
session.sendStartActivityRealtime();

// Stream user audio data while the user speaks.
session.sendAudioRealtime(audioData);

// Signal the end of user activity (for example, on button release) to trigger model response.
session.sendStopActivityRealtime();

Not yet supported for Web apps - check back soon!

// If you disable automatic voice activity detection (VAD), you need to manually demarcate user activity.

// Signal the start of user activity (for example, on push-to-talk button press).
await session.sendStartActivityRealtime();

// Stream user audio data while the user speaks.
await session.sendAudioRealtime(audioData);

// Signal the end of user activity (for example, on button release) to trigger model response.
await session.sendStopActivityRealtime();

// If you disable automatic voice activity detection (VAD), you need to manually demarcate user activity.

// Signal the start of user activity (for example, on push-to-talk button press).
await session.SendStartActivityRealtimeAsync();

// Stream user audio data while the user speaks.
await session.SendAudioRealtimeAsync(audio: audioData);

// Signal the end of user activity (for example, on button release) to trigger model response.
await session.SendStopActivityRealtimeAsync();