Azure AI Voicelive Java Agent Skill

<dependency>
    <groupId>com.azure</groupId>
    <artifactId>azure-ai-voicelive</artifactId>
    <version>1.0.0-beta.2</version>
</dependency>

AZURE_VOICELIVE_ENDPOINT=https://<resource>.openai.azure.com/ # Required for all auth methods
AZURE_VOICELIVE_API_KEY=<your-api-key> # Only required for AzureKeyCredential auth
AZURE_TOKEN_CREDENTIALS=prod  # Required only if DefaultAzureCredential is used in production

import com.azure.ai.voicelive.VoiceLiveAsyncClient;
import com.azure.ai.voicelive.VoiceLiveClientBuilder;
import com.azure.core.credential.AzureKeyCredential;

VoiceLiveAsyncClient client = new VoiceLiveClientBuilder()
    .endpoint(System.getenv("AZURE_VOICELIVE_ENDPOINT"))
    .credential(new AzureKeyCredential(System.getenv("AZURE_VOICELIVE_API_KEY")))
    .buildAsyncClient();

import com.azure.core.credential.TokenCredential;
import com.azure.identity.AzureIdentityEnvVars;
import com.azure.identity.DefaultAzureCredentialBuilder;
import com.azure.identity.ManagedIdentityCredentialBuilder;

TokenCredential credential = new DefaultAzureCredentialBuilder()
    .requireEnvVars(AzureIdentityEnvVars.AZURE_TOKEN_CREDENTIALS)
    .build();
// Or use a specific credential directly in production:
// See https://learn.microsoft.com/java/api/overview/azure/identity-readme?view=azure-java-stable#credential-classes
// TokenCredential credential = new ManagedIdentityCredentialBuilder().build();

VoiceLiveAsyncClient client = new VoiceLiveClientBuilder()
    .endpoint(System.getenv("AZURE_VOICELIVE_ENDPOINT"))
    .credential(credential)
    .buildAsyncClient();

import reactor.core.publisher.Mono;

client.startSession("gpt-4o-realtime-preview")
    .flatMap(session -> {
        System.out.println("Session started");
        
        // Subscribe to events
        session.receiveEvents()
            .subscribe(
                event -> System.out.println("Event: " + event.getType()),
                error -> System.err.println("Error: " + error.getMessage())
            );
        
        return Mono.just(session);
    })
    .block();

import com.azure.ai.voicelive.models.*;
import java.util.Arrays;

ServerVadTurnDetection turnDetection = new ServerVadTurnDetection()
    .setThreshold(0.5)                    // Sensitivity (0.0-1.0)
    .setPrefixPaddingMs(300)              // Audio before speech
    .setSilenceDurationMs(500)            // Silence to end turn
    .setInterruptResponse(true)           // Allow interruptions
    .setAutoTruncate(true)
    .setCreateResponse(true);

AudioInputTranscriptionOptions transcription = new AudioInputTranscriptionOptions(
    AudioInputTranscriptionOptionsModel.WHISPER_1);

VoiceLiveSessionOptions options = new VoiceLiveSessionOptions()
    .setInstructions("You are a helpful AI voice assistant.")
    .setVoice(BinaryData.fromObject(new OpenAIVoice(OpenAIVoiceName.ALLOY)))
    .setModalities(Arrays.asList(InteractionModality.TEXT, InteractionModality.AUDIO))
    .setInputAudioFormat(InputAudioFormat.PCM16)
    .setOutputAudioFormat(OutputAudioFormat.PCM16)
    .setInputAudioSamplingRate(24000)
    .setInputAudioNoiseReduction(new AudioNoiseReduction(AudioNoiseReductionType.NEAR_FIELD))
    .setInputAudioEchoCancellation(new AudioEchoCancellation())
    .setInputAudioTranscription(transcription)
    .setTurnDetection(turnDetection);

// Send configuration
ClientEventSessionUpdate updateEvent = new ClientEventSessionUpdate(options);
session.sendEvent(updateEvent).subscribe();

byte[] audioData = readAudioChunk(); // Your PCM16 audio data
session.sendInputAudio(BinaryData.fromBytes(audioData)).subscribe();

session.receiveEvents().subscribe(event -> {
    ServerEventType eventType = event.getType();
    
    if (ServerEventType.SESSION_CREATED.equals(eventType)) {
        System.out.println("Session created");
    } else if (ServerEventType.INPUT_AUDIO_BUFFER_SPEECH_STARTED.equals(eventType)) {
        System.out.println("User started speaking");
    } else if (ServerEventType.INPUT_AUDIO_BUFFER_SPEECH_STOPPED.equals(eventType)) {
        System.out.println("User stopped speaking");
    } else if (ServerEventType.RESPONSE_AUDIO_DELTA.equals(eventType)) {
        if (event instanceof SessionUpdateResponseAudioDelta) {
            SessionUpdateResponseAudioDelta audioEvent = (SessionUpdateResponseAudioDelta) event;
            playAudioChunk(audioEvent.getDelta());
        }
    } else if (ServerEventType.RESPONSE_DONE.equals(eventType)) {
        System.out.println("Response complete");
    } else if (ServerEventType.ERROR.equals(eventType)) {
        if (event instanceof SessionUpdateError) {
            SessionUpdateError errorEvent = (SessionUpdateError) event;
            System.err.println("Error: " + errorEvent.getError().getMessage());
        }
    }
});

// Available: ALLOY, ASH, BALLAD, CORAL, ECHO, SAGE, SHIMMER, VERSE
VoiceLiveSessionOptions options = new VoiceLiveSessionOptions()
    .setVoice(BinaryData.fromObject(new OpenAIVoice(OpenAIVoiceName.ALLOY)));

// Azure Standard Voice
options.setVoice(BinaryData.fromObject(new AzureStandardVoice("en-US-JennyNeural")));

// Azure Custom Voice
options.setVoice(BinaryData.fromObject(new AzureCustomVoice("myVoice", "endpointId")));

// Azure Personal Voice
options.setVoice(BinaryData.fromObject(
    new AzurePersonalVoice("speakerProfileId", PersonalVoiceModels.PHOENIX_LATEST_NEURAL)));

VoiceLiveFunctionDefinition weatherFunction = new VoiceLiveFunctionDefinition("get_weather")
    .setDescription("Get current weather for a location")
    .setParameters(BinaryData.fromObject(parametersSchema));

VoiceLiveSessionOptions options = new VoiceLiveSessionOptions()
    .setTools(Arrays.asList(weatherFunction))
    .setInstructions("You have access to weather information.");

session.receiveEvents()
    .doOnError(error -> System.err.println("Connection error: " + error.getMessage()))
    .onErrorResume(error -> {
        // Attempt reconnection or cleanup
        return Flux.empty();
    })
    .subscribe();