[VoiceLive] Add built-in OpenTelemetry tracing support

sdk/voicelive/azure-ai-voicelive/CHANGELOG.md

@@ -4,6 +4,15 @@
 
 ### Features Added
 
+- Added built-in OpenTelemetry tracing support for voice sessions following GenAI Semantic Conventions:
+  - `VoiceLiveClientBuilder.openTelemetry(OpenTelemetry)` method for providing a custom OpenTelemetry instance
+  - Defaults to `GlobalOpenTelemetry.getOrNoop()` for automatic Java agent detection with zero-cost no-op fallback
+  - Emits spans for `connect`, `send`, `recv`, and `close` operations with voice-specific attributes
+  - Session-level counters: turn count, interruption count, audio bytes sent/received, first token latency
+  - Per-message attributes: token usage, event types, error details
+  - Content recording controlled via `enableContentRecording(boolean)` or `AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED` environment variable
+- Added `TelemetrySample.java` demonstrating OpenTelemetry integration patterns
+
 ### Breaking Changes
 
 ### Bugs Fixed

sdk/voicelive/azure-ai-voicelive/README.md

@@ -126,6 +126,7 @@ The following sections provide code snippets for common scenarios:
 * [Handle event types](#handle-event-types)
 * [Voice configuration](#voice-configuration)
 * [Function calling](#function-calling)
+* [Telemetry and tracing](#telemetry-and-tracing)
 * [Complete voice assistant with microphone](#complete-voice-assistant-with-microphone)
 
 ### Focused Sample Files
@@ -166,6 +167,12 @@ For easier learning, explore these focused samples in order:
    - Execute functions locally and return results
    - Continue conversation with function results
 
+7. **TelemetrySample.java** - OpenTelemetry tracing integration
+   - Automatic tracing via GlobalOpenTelemetry (zero-config)
+   - Explicit OpenTelemetry instance via builder
+   - Span structure and session-level attributes
+   - Azure Monitor integration example
+
 > **Note:** To run audio samples (AudioPlaybackSample, MicrophoneInputSample, VoiceAssistantSample, FunctionCallingSample):
 > ```bash
 > mvn exec:java -Dexec.mainClass=com.azure.ai.voicelive.FunctionCallingSample -Dexec.classpathScope=test
@@ -397,6 +404,74 @@ client.startSession("gpt-4o-realtime-preview")
 * Results are sent back to continue the conversation
 * See `FunctionCallingSample.java` for a complete working example
 
+### Telemetry and tracing
+
+The SDK has built-in [OpenTelemetry](https://opentelemetry.io/) tracing that emits spans for every WebSocket operation. When no OpenTelemetry SDK is present, all tracing calls are automatically no-op with zero performance impact.
+
+#### Automatic tracing (recommended)
+
+If the [OpenTelemetry Java agent](https://opentelemetry.io/docs/languages/java/automatic/) is attached, or `GlobalOpenTelemetry` is configured, tracing works automatically with no code changes:
+
+```java com.azure.ai.voicelive.tracing.automatic
+// No special configuration needed — tracing is picked up from GlobalOpenTelemetry
+VoiceLiveAsyncClient client = new VoiceLiveClientBuilder()
+    .endpoint(endpoint)
+    .credential(new AzureKeyCredential(apiKey))
+    .buildAsyncClient();
+```
+
+#### Explicit OpenTelemetry instance
+
+Provide your own `OpenTelemetry` instance to control trace export:
+
+```java com.azure.ai.voicelive.tracing.explicit
+VoiceLiveAsyncClient client = new VoiceLiveClientBuilder()
+    .endpoint(endpoint)
+    .credential(new AzureKeyCredential(apiKey))
+    .openTelemetry(otel)
+    .buildAsyncClient();
+```
+
+#### Span structure
+
+When tracing is active, the following span hierarchy is emitted for each voice session:
+
+```
+connect gpt-4o-realtime-preview        ← session lifetime span
+├── send session.update                 ← one span per sent event
+├── send response.create
+├── recv session.created                ← one span per received event
+├── recv response.audio.delta
+├── recv response.done                  ← includes token usage attributes
+└── close
+```
+
+**Session-level attributes** (on the connect span):
+- `gen_ai.system` — `openai`
+- `gen_ai.request.model` — Model name (e.g., `gpt-4o-realtime-preview`)
+- `server.address` — Service endpoint
+- `gen_ai.voice.session_id` — Voice session ID
+- `gen_ai.voice.turn_count` — Completed response turns
+- `gen_ai.voice.interruption_count` — User interruptions
+- `gen_ai.voice.audio_bytes_sent` / `audio_bytes_received` — Audio payload bytes
+- `gen_ai.voice.first_token_latency_ms` — Time to first audio response
+
+#### Content recording
+
+By default, message payloads are not recorded in spans for privacy. Enable content recording via the builder or environment variable:
+
+```java
+// Via builder
+new VoiceLiveClientBuilder()
+    .enableContentRecording(true)
+    // ...
+
+// Or via environment variable
+// AZURE_TRACING_GEN_AI_CONTENT_RECORDING_ENABLED=true
+```
+
+> See `TelemetrySample.java` for complete tracing examples including Azure Monitor integration.
+
 ### Complete voice assistant with microphone
 
 A full example demonstrating real-time microphone input and audio playback:

sdk/voicelive/azure-ai-voicelive/checkstyle-suppressions.xml

@@ -3,6 +3,18 @@
 <!-- This file is generated by the /eng/scripts/linting_suppression_generator.py script. -->
 
 <suppressions>
+  <!-- OpenTelemetry tracing imports -->
+  <suppress files="com.azure.ai.voicelive.VoiceLiveTracer.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceLiveAsyncClient.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceLiveClientBuilder.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceLiveClientBuilder.java" checks="io.clientcore.linting.extensions.checkstyle.checks.ExternalDependencyExposedCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceLiveSessionAsyncClient.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceLiveTracerTest.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceLiveClientBuilderTest.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.ReadmeSamples.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.TelemetrySample.java" checks="IllegalImportCheck" />
+  <suppress files="com.azure.ai.voicelive.VoiceAssistantSample.java" checks="IllegalImportCheck" />
+
   <suppress files="com.azure.ai.voicelive.models.AssistantMessageItem.java" checks="io.clientcore.linting.extensions.checkstyle.checks.EnforceFinalFieldsCheck" />
   <suppress files="com.azure.ai.voicelive.models.MessageItem.java" checks="io.clientcore.linting.extensions.checkstyle.checks.EnforceFinalFieldsCheck" />
   <suppress files="com.azure.ai.voicelive.models.SystemMessageItem.java" checks="io.clientcore.linting.extensions.checkstyle.checks.EnforceFinalFieldsCheck" />

sdk/voicelive/azure-ai-voicelive/pom.xml

@@ -56,6 +56,11 @@ Code generated by Microsoft (R) TypeSpec Code Generator.
       <artifactId>azure-core-http-netty</artifactId>
       <version>1.16.3</version> <!-- {x-version-update;com.azure:azure-core-http-netty;dependency} -->
     </dependency>
+    <dependency>
+      <groupId>io.opentelemetry</groupId>
+      <artifactId>opentelemetry-api</artifactId>
+      <version>1.58.0</version> <!-- {x-version-update;io.opentelemetry:opentelemetry-api;external_dependency} -->
+    </dependency>
     <dependency>
       <groupId>com.azure</groupId>
       <artifactId>azure-core-test</artifactId>
@@ -82,5 +87,42 @@ Code generated by Microsoft (R) TypeSpec Code Generator.
       <version>3.7.11</version> <!-- {x-version-update;io.projectreactor:reactor-test;external_dependency} -->
       <scope>test</scope>
     </dependency>
+    <dependency>
+      <groupId>io.opentelemetry</groupId>
+      <artifactId>opentelemetry-sdk</artifactId>
+      <version>1.58.0</version> <!-- {x-version-update;io.opentelemetry:opentelemetry-sdk;external_dependency} -->
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>io.opentelemetry</groupId>
+      <artifactId>opentelemetry-sdk-testing</artifactId>
+      <version>1.58.0</version> <!-- {x-version-update;io.opentelemetry:opentelemetry-sdk-testing;external_dependency} -->
+      <scope>test</scope>
+    </dependency>
+    <dependency>
+      <groupId>io.opentelemetry</groupId>
+      <artifactId>opentelemetry-exporter-logging</artifactId>
+      <version>1.58.0</version> <!-- {x-version-update;io.opentelemetry:opentelemetry-exporter-logging;external_dependency} -->
+      <scope>test</scope>
+    </dependency>
   </dependencies>
+
+  <build>
+    <plugins>
+      <plugin>
+        <groupId>org.apache.maven.plugins</groupId>
+        <artifactId>maven-enforcer-plugin</artifactId>
+        <version>3.6.1</version> <!-- {x-version-update;org.apache.maven.plugins:maven-enforcer-plugin;external_dependency} -->
+        <configuration>
+          <rules>
+            <bannedDependencies>
+              <includes>
+                <include>io.opentelemetry:opentelemetry-api:[1.58.0]</include> <!-- {x-include-update;io.opentelemetry:opentelemetry-api;external_dependency} -->
+              </includes>
+            </bannedDependencies>
+          </rules>
+        </configuration>
+      </plugin>
+    </plugins>
+  </build>
 </project>

sdk/voicelive/azure-ai-voicelive/src/main/java/com/azure/ai/voicelive/VoiceLiveAsyncClient.java

@@ -18,6 +18,7 @@
 import com.azure.core.http.HttpHeaderName;
 import com.azure.core.http.HttpHeaders;
 import com.azure.core.util.logging.ClientLogger;
+import io.opentelemetry.api.trace.Tracer;
 
 import reactor.core.publisher.Mono;
 
@@ -34,6 +35,8 @@ public final class VoiceLiveAsyncClient {
     private final TokenCredential tokenCredential;
     private final String apiVersion;
     private final HttpHeaders additionalHeaders;
+    private final Tracer tracer;
+    private final Boolean enableContentRecording;
 
     /**
      * Creates a VoiceLiveAsyncClient with API key authentication.
@@ -44,11 +47,28 @@ public final class VoiceLiveAsyncClient {
      * @param additionalHeaders Additional headers to include in requests.
      */
     VoiceLiveAsyncClient(URI endpoint, KeyCredential keyCredential, String apiVersion, HttpHeaders additionalHeaders) {
+        this(endpoint, keyCredential, apiVersion, additionalHeaders, null, null);
+    }
+
+    /**
+     * Creates a VoiceLiveAsyncClient with API key authentication and tracing.
+     *
+     * @param endpoint The service endpoint.
+     * @param keyCredential The API key credential.
+     * @param apiVersion The API version.
+     * @param additionalHeaders Additional headers to include in requests.
+     * @param tracer The OpenTelemetry Tracer for instrumentation (may be a no-op tracer).
+     * @param enableContentRecording Override for content recording, or null to use env var.
+     */
+    VoiceLiveAsyncClient(URI endpoint, KeyCredential keyCredential, String apiVersion, HttpHeaders additionalHeaders,
+        Tracer tracer, Boolean enableContentRecording) {
         this.endpoint = Objects.requireNonNull(endpoint, "'endpoint' cannot be null");
         this.keyCredential = Objects.requireNonNull(keyCredential, "'keyCredential' cannot be null");
         this.tokenCredential = null;
         this.apiVersion = Objects.requireNonNull(apiVersion, "'apiVersion' cannot be null");
         this.additionalHeaders = additionalHeaders != null ? additionalHeaders : new HttpHeaders();
+        this.tracer = tracer;
+        this.enableContentRecording = enableContentRecording;
     }
 
     /**
@@ -61,11 +81,28 @@ public final class VoiceLiveAsyncClient {
      */
     VoiceLiveAsyncClient(URI endpoint, TokenCredential tokenCredential, String apiVersion,
         HttpHeaders additionalHeaders) {
+        this(endpoint, tokenCredential, apiVersion, additionalHeaders, null, null);
+    }
+
+    /**
+     * Creates a VoiceLiveAsyncClient with token authentication and tracing.
+     *
+     * @param endpoint The service endpoint.
+     * @param tokenCredential The token credential.
+     * @param apiVersion The API version.
+     * @param additionalHeaders Additional headers to include in requests.
+     * @param tracer The OpenTelemetry Tracer for instrumentation (may be a no-op tracer).
+     * @param enableContentRecording Override for content recording, or null to use env var.
+     */
+    VoiceLiveAsyncClient(URI endpoint, TokenCredential tokenCredential, String apiVersion,
+        HttpHeaders additionalHeaders, Tracer tracer, Boolean enableContentRecording) {
         this.endpoint = Objects.requireNonNull(endpoint, "'endpoint' cannot be null");
         this.keyCredential = null;
         this.tokenCredential = Objects.requireNonNull(tokenCredential, "'tokenCredential' cannot be null");
         this.apiVersion = Objects.requireNonNull(apiVersion, "'apiVersion' cannot be null");
         this.additionalHeaders = additionalHeaders != null ? additionalHeaders : new HttpHeaders();
+        this.tracer = tracer;
+        this.enableContentRecording = enableContentRecording;
     }
 
     /**
@@ -79,12 +116,7 @@ public Mono<VoiceLiveSessionAsyncClient> startSession(String model) {
         Objects.requireNonNull(model, "'model' cannot be null");
 
         return Mono.fromCallable(() -> convertToWebSocketEndpoint(endpoint, model)).flatMap(wsEndpoint -> {
-            VoiceLiveSessionAsyncClient session;
-            if (keyCredential != null) {
-                session = new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential);
-            } else {
-                session = new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential);
-            }
+            VoiceLiveSessionAsyncClient session = createSessionClient(wsEndpoint, model);
             return session.connect(additionalHeaders).thenReturn(session);
         });
     }
@@ -97,12 +129,7 @@ public Mono<VoiceLiveSessionAsyncClient> startSession(String model) {
      */
     public Mono<VoiceLiveSessionAsyncClient> startSession() {
         return Mono.fromCallable(() -> convertToWebSocketEndpoint(endpoint, null)).flatMap(wsEndpoint -> {
-            VoiceLiveSessionAsyncClient session;
-            if (keyCredential != null) {
-                session = new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential);
-            } else {
-                session = new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential);
-            }
+            VoiceLiveSessionAsyncClient session = createSessionClient(wsEndpoint, null);
             return session.connect(additionalHeaders).thenReturn(session);
         });
     }
@@ -122,12 +149,7 @@ public Mono<VoiceLiveSessionAsyncClient> startSession(String model, VoiceLiveReq
         return Mono
             .fromCallable(() -> convertToWebSocketEndpoint(endpoint, model, requestOptions.getCustomQueryParameters()))
             .flatMap(wsEndpoint -> {
-                VoiceLiveSessionAsyncClient session;
-                if (keyCredential != null) {
-                    session = new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential);
-                } else {
-                    session = new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential);
-                }
+                VoiceLiveSessionAsyncClient session = createSessionClient(wsEndpoint, model);
                 // Merge additional headers with custom headers from requestOptions
                 HttpHeaders mergedHeaders = mergeHeaders(additionalHeaders, requestOptions.getCustomHeaders());
                 return session.connect(mergedHeaders).thenReturn(session);
@@ -148,12 +170,7 @@ public Mono<VoiceLiveSessionAsyncClient> startSession(VoiceLiveRequestOptions re
         return Mono
             .fromCallable(() -> convertToWebSocketEndpoint(endpoint, null, requestOptions.getCustomQueryParameters()))
             .flatMap(wsEndpoint -> {
-                VoiceLiveSessionAsyncClient session;
-                if (keyCredential != null) {
-                    session = new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential);
-                } else {
-                    session = new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential);
-                }
+                VoiceLiveSessionAsyncClient session = createSessionClient(wsEndpoint, null);
                 // Merge additional headers with custom headers from requestOptions
                 HttpHeaders mergedHeaders = mergeHeaders(additionalHeaders, requestOptions.getCustomHeaders());
                 return session.connect(mergedHeaders).thenReturn(session);
@@ -176,12 +193,7 @@ public Mono<VoiceLiveSessionAsyncClient> startSession(AgentSessionConfig agentCo
 
         return Mono.fromCallable(() -> convertToWebSocketEndpoint(endpoint, null, agentConfig.toQueryParameters()))
             .flatMap(wsEndpoint -> {
-                VoiceLiveSessionAsyncClient session;
-                if (keyCredential != null) {
-                    session = new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential);
-                } else {
-                    session = new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential);
-                }
+                VoiceLiveSessionAsyncClient session = createSessionClient(wsEndpoint, null);
                 return session.connect(additionalHeaders).thenReturn(session);
             });
     }
@@ -211,18 +223,28 @@ public Mono<VoiceLiveSessionAsyncClient> startSession(AgentSessionConfig agentCo
         }
 
         return Mono.fromCallable(() -> convertToWebSocketEndpoint(endpoint, null, mergedParams)).flatMap(wsEndpoint -> {
-            VoiceLiveSessionAsyncClient session;
-            if (keyCredential != null) {
-                session = new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential);
-            } else {
-                session = new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential);
-            }
+            VoiceLiveSessionAsyncClient session = createSessionClient(wsEndpoint, null);
             // Merge additional headers with custom headers from requestOptions
             HttpHeaders mergedHeaders = mergeHeaders(additionalHeaders, requestOptions.getCustomHeaders());
             return session.connect(mergedHeaders).thenReturn(session);
         });
     }
 
+    /**
+     * Creates a VoiceLiveSessionAsyncClient with the appropriate credentials and optional tracing.
+     *
+     * @param wsEndpoint The WebSocket endpoint URI.
+     * @param model The model name, used for tracing span names.
+     * @return A new VoiceLiveSessionAsyncClient instance.
+     */
+    private VoiceLiveSessionAsyncClient createSessionClient(URI wsEndpoint, String model) {
+        if (keyCredential != null) {
+            return new VoiceLiveSessionAsyncClient(wsEndpoint, keyCredential, tracer, model, enableContentRecording);
+        } else {
+            return new VoiceLiveSessionAsyncClient(wsEndpoint, tokenCredential, tracer, model, enableContentRecording);
+        }
+    }
+
     /**
      * Merges two HttpHeaders objects, with custom headers taking precedence.
      *