[VoiceLive] Release initial GA version 1.0.0

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

@@ -1,9 +1,38 @@
 # Release History
 
-## 1.0.0 (Unreleased)
+## 1.0.0 (2026-05-25)
 
 This is the first General Availability (GA) release of the Azure VoiceLive client library for Java.
 
+### Breaking Changes
+
+- Narrowed `VoiceLiveAsyncClient` session startup to three overloads:
+  - `startSession()`
+  - `startSession(String, VoiceLiveRequestOptions)`
+  - `startSession(AgentSessionConfig, VoiceLiveRequestOptions)`
+- Renamed token-count accessors on token statistic models (JSON wire format unchanged):
+  - `CachedTokenDetails.getTextTokens()` / `getAudioTokens()` / `getImageTokens()` → `getTextTokenCount()` / `getAudioTokenCount()` / `getImageTokenCount()`
+  - `InputTokenDetails.getCachedTokens()` / `getTextTokens()` / `getAudioTokens()` / `getImageTokens()` → `getCachedTokenCount()` / `getTextTokenCount()` / `getAudioTokenCount()` / `getImageTokenCount()`
+  - `OutputTokenDetails.getTextTokens()` / `getAudioTokens()` / `getReasoningTokens()` → `getTextTokenCount()` / `getAudioTokenCount()` / `getReasoningTokenCount()`
+  - `ResponseTokenStatistics.getTotalTokens()` / `getInputTokens()` / `getOutputTokens()` → `getTotalTokenCount()` / `getInputTokenCount()` / `getOutputTokenCount()`
+- `RequestImageContentPart` URL accessor renamed and JSON field changed:
+  - `getUrl()` / `setUrl(String)` → `getImageUrl()` / `setImageUrl(String)`
+  - JSON property `url` → `image_url`
+- Renamed base event types for client↔server symmetry:
+  - `ClientEvent` (base for outbound events) → `SessionClientEvent`
+  - `SessionUpdate` (base for inbound events) → `SessionServerEvent`
+  - `VoiceLiveSessionAsyncClient.receiveEvents()` now returns `Flux<SessionServerEvent>`
+  - `VoiceLiveSessionAsyncClient.sendEvent(...)` now accepts `SessionClientEvent`
+- Renamed MCP-related model types to Pascal case (`MCP*` → `Mcp*`): `McpApprovalType`, `McpServer`, `McpTool`, `McpApprovalResponseRequestItem`, `ResponseMcpApprovalRequestItem`, `ResponseMcpApprovalResponseItem`, `ResponseMcpCallItem`, `ResponseMcpListToolItem`.
+- `VoiceLiveSessionAsyncClient.truncateConversation(String, int, int)` now accepts a `java.time.Duration` for the audio-end position instead of raw milliseconds. The two-argument overload (`itemId`, `contentIndex`) is preserved and defaults to `Duration.ZERO`.
+- Removed `sendInputAudio(byte[])`; use `sendInputAudio(BinaryData)` (wrap raw bytes with `BinaryData.fromBytes(...)`).
+- `AgentSessionConfig.toQueryParameters()` is no longer part of the public API; the conversion is handled internally by `VoiceLiveAsyncClient`.
+- `VoiceLiveSessionOptions.setAnimation(...)` renamed to `setAnimationOptions(...)`.
+- `AnimationOptions.setOutputs(...)` / `getOutputs()` renamed to `setOutputTypes(...)` / `getOutputTypes()`.
+- `LogProbProperties.getLogprob()` renamed to `getLogProb()`.
+- `SessionUpdateConversationItemInputAudioTranscriptionCompleted.getLogprobs()` renamed to `getLogProbs()`.
+- Removed preview service versions from `VoiceLiveServiceVersion`; only GA versions remain (`V2025_10_01`, `V2026_04_10`). The latest version is now `V2026_04_10`.
+
 ### Features Added
 
 - **Avatar voice synchronization** for video avatars:
@@ -18,19 +47,20 @@ This is the first General Availability (GA) release of the Azure VoiceLive clien
 - **Transcription enhancements**:
   - New transcription models on `AudioInputTranscriptionOptionsModel`: `GPT_4O_TRANSCRIBE_DIARIZE`, `MAI_TRANSCRIBE_1`
   - New `TranscriptionPhrase` and `TranscriptionWord` types with timing/confidence information
-  - `SessionUpdateConversationItemInputAudioTranscriptionCompleted` now exposes `getLogprobs()` and `getPhrases()`
+  - `SessionUpdateConversationItemInputAudioTranscriptionCompleted` now exposes `getLogProbs()` and `getPhrases()`
   - New `ServerEventResponseAudioTranscriptAnnotationAdded` event
 - **Session include options and metadata**:
   - New `SessionIncludeOption` expandable enum for opting into additional response payloads (e.g. logprobs, phrases, file-search results)
   - `VoiceLiveSessionOptions` and `VoiceLiveSessionResponse` now expose `include` (`List<SessionIncludeOption>`) and `metadata` (`Map<String,String>`, up to 16 entries)
 - **Personal voice models**: added `PersonalVoiceModels.DRAGON_HDOMNI_LATEST_NEURAL` and `MAI_VOICE_1`
-- **Reasoning token usage**: `OutputTokenDetails.getReasoningTokens()` exposes reasoning token counts
+- **Reasoning token usage**: `OutputTokenDetails.getReasoningTokenCount()` exposes reasoning token counts
 - **Interim response on response.create**: `ResponseCreateParams.setInterimResponse(BinaryData)` lets callers attach interim response config to a single response request
+- Restored no-arg `VoiceLiveAsyncClient.startSession()` overload (uses the deployment's default model).
 - Significantly improved Javadoc for `ServerVadTurnDetection`, `AzureCustomVoice`, `AzurePersonalVoice`, `AzureStandardVoice`, `AzureSemanticVadTurnDetection*`, and other model types
 
 ### Other Changes
 
-- Updated default service API version to track the latest TypeSpec spec.
+- Updated default service API version to `2026-04-10` (GA).
 
 ## 1.0.0-beta.6 (2026-05-01)
 

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

@@ -193,13 +193,23 @@ For easier learning, explore these focused samples in order:
 > ```
 > These samples use `javax.sound.sampled` for audio I/O.
 
+### Session startup overloads
+
+`VoiceLiveAsyncClient` exposes three session-start overloads:
+
+- `startSession()`
+- `startSession(String model, VoiceLiveRequestOptions options)`
+- `startSession(AgentSessionConfig agentConfig, VoiceLiveRequestOptions options)`
+
+Pass `null` for `VoiceLiveRequestOptions` in the samples below when you do not need to provide one.
+
 ### Simple voice assistant
 
 Create a basic voice assistant session:
 
 ```java com.azure.ai.voicelive.simple.session
-// Start session with default options
-client.startSession("gpt-realtime")
+// Start session with a specific model; pass null when no VoiceLiveRequestOptions value is needed
+client.startSession("gpt-realtime", null)
     .flatMap(session -> {
         System.out.println("Session started");
 
@@ -243,8 +253,8 @@ VoiceLiveSessionOptions options = new VoiceLiveSessionOptions()
     .setInputAudioTranscription(transcription)
     .setTurnDetection(turnDetection);
 
-// Start session with options
-client.startSession("gpt-realtime")
+// Start session and then send session configuration
+client.startSession("gpt-realtime", null)
     .flatMap(session -> {
         // Send session configuration
         ClientEventSessionUpdate updateEvent = new ClientEventSessionUpdate(options);
@@ -370,7 +380,7 @@ VoiceLiveSessionOptions options = new VoiceLiveSessionOptions()
     .setInstructions("You have access to weather information. Use get_current_weather when asked about weather.");
 
 // 3. Handle function call events
-client.startSession("gpt-realtime")
+client.startSession("gpt-realtime", null)
     .flatMap(session -> {
         return session.receiveEvents()
             .doOnNext(event -> {
@@ -422,8 +432,8 @@ Use [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) servers to
 
 ```java com.azure.ai.voicelive.mcp
 // Configure MCP servers as tools
-MCPServer mcpServer = new MCPServer("deepwiki", "https://mcp.deepwiki.com/mcp")
-    .setRequireApproval(BinaryData.fromObject(MCPApprovalType.ALWAYS));
+McpServer mcpServer = new McpServer("deepwiki", "https://mcp.deepwiki.com/mcp")
+    .setRequireApproval(BinaryData.fromObject(McpApprovalType.ALWAYS));
 
 VoiceLiveSessionOptions options = new VoiceLiveSessionOptions()
     .setTools(Arrays.asList(mcpServer))
@@ -436,10 +446,10 @@ session.receiveEvents()
             SessionUpdateResponseOutputItemDone itemDone = (SessionUpdateResponseOutputItemDone) event;
             SessionResponseItem item = itemDone.getItem();
 
-            if (item instanceof ResponseMCPApprovalRequestItem) {
+            if (item instanceof ResponseMcpApprovalRequestItem) {
                 // Approve the tool call
-                ResponseMCPApprovalRequestItem approvalRequest = (ResponseMCPApprovalRequestItem) item;
-                MCPApprovalResponseRequestItem approval = new MCPApprovalResponseRequestItem(
+                ResponseMcpApprovalRequestItem approvalRequest = (ResponseMcpApprovalRequestItem) item;
+                McpApprovalResponseRequestItem approval = new McpApprovalResponseRequestItem(
                     approvalRequest.getId(), true);
                 ClientEventConversationItemCreate createItem = new ClientEventConversationItemCreate()
                     .setItem(approval);
@@ -464,13 +474,13 @@ Connect directly to an Azure AI Foundry agent using `AgentSessionConfig`. The ag
 AgentSessionConfig agentConfig = new AgentSessionConfig("my-agent", "my-project")
     .setAgentVersion("1.0");
 
-// Start session with agent config (uses DefaultAzureCredential)
+// Start session with agent config; pass null when no VoiceLiveRequestOptions value is needed
 VoiceLiveAsyncClient client = new VoiceLiveClientBuilder()
     .endpoint(endpoint)
     .credential(new DefaultAzureCredentialBuilder().build())
     .buildAsyncClient();
 
-client.startSession(agentConfig)
+client.startSession(agentConfig, null)
     .flatMap(session -> {
         return session.receiveEvents()
             .doOnNext(event -> handleEvent(event))
@@ -596,8 +606,8 @@ VoiceLiveSessionOptions sessionOptions = new VoiceLiveSessionOptions()
     .setInputAudioTranscription(transcriptionOptions)
     .setTurnDetection(turnDetection);
 
-// Start session and handle events
-client.startSession("gpt-4o-realtime-preview")
+// Start session (null VoiceLiveRequestOptions), then handle events
+client.startSession("gpt-4o-realtime-preview", null)
     .flatMap(session -> {
         // Subscribe to receive server events
         session.receiveEvents()