[draft][VoiceLive] Add support for built-in web search and file search tools

.vscode/cspell.json

@@ -1498,6 +1498,8 @@
         "FOUNDRY",
         "genai",
         "GENAI",
+        "HDOMNI",
+        "SSML",
         "Unpooled",
         "viseme",
         "VISEME",

eng/versioning/version_client.txt

@@ -60,7 +60,7 @@ com.azure:azure-ai-textanalytics-perf;1.0.0-beta.1;1.0.0-beta.1
 com.azure:azure-ai-translation-text;1.1.8;2.0.0-beta.2
 com.azure:azure-ai-translation-document;1.0.7;1.1.0-beta.1
 com.azure:azure-ai-vision-face;1.0.0-beta.2;1.0.0-beta.3
-com.azure:azure-ai-voicelive;1.0.0-beta.6;1.0.0-beta.7
+com.azure:azure-ai-voicelive;1.0.0-beta.6;1.0.0
 com.azure:azure-analytics-defender-easm;1.0.0-beta.1;1.0.0-beta.2
 com.azure:azure-analytics-purview-datamap;1.0.0-beta.2;1.0.0-beta.3
 com.azure:azure-analytics-onlineexperimentation;1.0.0-beta.1;1.0.0-beta.2

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

@@ -1,15 +1,41 @@
 # Release History
 
-## 1.0.0-beta.7 (Unreleased)
+## 1.0.0 (Unreleased)
+
+This is the first General Availability (GA) release of the Azure VoiceLive client library for Java.
 
 ### Features Added
 
+- **Avatar voice synchronization** for video avatars:
+  - New `AzureVoiceType.AVATAR_VOICE_SYNC` and `AzureAvatarVoiceSyncVoice` class
+  - New server events `ServerEventSessionAvatarSwitchToSpeaking` / `ServerEventSessionAvatarSwitchToIdle`
+  - New `ServerEventResponseVideoDelta` for streaming avatar video frames
+  - New `ClientEventOutputAudioBufferClear` (`output_audio_buffer.clear`) and `ServerEventOutputAudioBufferCleared` (`output_audio_buffer.cleared`) for clearing the avatar output audio buffer
+- **Web search and file search tool calls**:
+  - New `ItemType.WEB_SEARCH_CALL`, `ItemType.FILE_SEARCH_CALL`
+  - New `ResponseWebSearchCallItem` (with `ResponseWebSearchCallItemStatus`) and `ResponseFileSearchCallItem` (with `ResponseFileSearchCallItemStatus`, plus `FileSearchResult` results)
+  - New lifecycle server events: `ServerEventResponseWebSearchCall{Searching,InProgress,Completed}` and `ServerEventResponseFileSearchCall{Searching,InProgress,Completed}`
+- **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()`
+  - 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
+- **Interim response on response.create**: `ResponseCreateParams.setInterimResponse(BinaryData)` lets callers attach interim response config to a single response request
+- Significantly improved Javadoc for `ServerVadTurnDetection`, `AzureCustomVoice`, `AzurePersonalVoice`, `AzureStandardVoice`, `AzureSemanticVadTurnDetection*`, and other model types
+
 ### Breaking Changes
 
-### Bugs Fixed
+- Removed `PersonalVoiceModels.PHOENIX_V2NEURAL` (no longer supported by the service). Use `PHOENIX_LATEST_NEURAL` or one of the new `DRAGON_*` / `MAI_VOICE_1` models instead.
 
 ### Other Changes
 
+- Updated default service API version to track the latest TypeSpec spec.
+
 ## 1.0.0-beta.6 (2026-05-01)
 
 ### Features Added

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

@@ -27,7 +27,7 @@ Use the Azure VoiceLive client library for Java to:
 <dependency>
     <groupId>com.azure</groupId>
     <artifactId>azure-ai-voicelive</artifactId>
-    <version>1.0.0-beta.2</version>
+    <version>1.0.0</version>
 </dependency>
 ```
 [//]: # ({x-version-update-end})
@@ -347,7 +347,7 @@ VoiceLiveSessionOptions options2 = new VoiceLiveSessionOptions()
     .setVoice(BinaryData.fromObject(new AzureCustomVoice("myCustomVoice", "myEndpointId")));
 
 // Azure Personal Voice - requires speaker profile ID and model
-// Models: DRAGON_LATEST_NEURAL, PHOENIX_LATEST_NEURAL, PHOENIX_V2NEURAL
+// Models: DRAGON_LATEST_NEURAL, DRAGON_HDOMNI_LATEST_NEURAL, PHOENIX_LATEST_NEURAL, MAI_VOICE_1
 VoiceLiveSessionOptions options3 = new VoiceLiveSessionOptions()
     .setVoice(BinaryData.fromObject(
         new AzurePersonalVoice("speakerProfileId", PersonalVoiceModels.PHOENIX_LATEST_NEURAL)));

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

@@ -14,7 +14,7 @@ Code generated by Microsoft (R) TypeSpec Code Generator.
 
   <groupId>com.azure</groupId>
   <artifactId>azure-ai-voicelive</artifactId>
-  <version>1.0.0-beta.7</version> <!-- {x-version-update;com.azure:azure-ai-voicelive;current} -->
+  <version>1.0.0</version> <!-- {x-version-update;com.azure:azure-ai-voicelive;current} -->
   <packaging>jar</packaging>
 
   <name>Microsoft Azure SDK for VoiceLive</name>

sdk/voicelive/azure-ai-voicelive/src/main/java/com/azure/ai/voicelive/models/AudioInputTranscriptionOptions.java

@@ -22,7 +22,7 @@ public final class AudioInputTranscriptionOptions implements JsonSerializable<Au
     /*
      * The transcription model to use. Supported values:
      * 'whisper-1', 'gpt-4o-transcribe', 'gpt-4o-mini-transcribe',
-     * 'azure-speech'.
+     * 'mai-transcribe-1', 'azure-speech'.
      */
     @Generated
     private final AudioInputTranscriptionOptionsModel model;
@@ -59,7 +59,7 @@ public AudioInputTranscriptionOptions(AudioInputTranscriptionOptionsModel model)
     /**
      * Get the model property: The transcription model to use. Supported values:
      * 'whisper-1', 'gpt-4o-transcribe', 'gpt-4o-mini-transcribe',
-     * 'azure-speech'.
+     * 'mai-transcribe-1', 'azure-speech'.
      *
      * @return the model value.
      */

sdk/voicelive/azure-ai-voicelive/src/main/java/com/azure/ai/voicelive/models/AudioInputTranscriptionOptionsModel.java

@@ -68,4 +68,17 @@ public static AudioInputTranscriptionOptionsModel fromString(String name) {
     public static Collection<AudioInputTranscriptionOptionsModel> values() {
         return values(AudioInputTranscriptionOptionsModel.class);
     }
+
+    /**
+     * Static value gpt-4o-transcribe-diarize for AudioInputTranscriptionOptionsModel.
+     */
+    @Generated
+    public static final AudioInputTranscriptionOptionsModel GPT_4O_TRANSCRIBE_DIARIZE
+        = fromString("gpt-4o-transcribe-diarize");
+
+    /**
+     * Static value mai-transcribe-1 for AudioInputTranscriptionOptionsModel.
+     */
+    @Generated
+    public static final AudioInputTranscriptionOptionsModel MAI_TRANSCRIBE_1 = fromString("mai-transcribe-1");
 }