Merge pull request #4516 from MicrosoftDocs/main

Merged by Learn.Build PR Management system

Author: learn-build-service-prod[bot]

articles/ai-foundry/whats-new-azure-ai-foundry.md

@@ -1,36 +1,39 @@
 ---
-title: "Azure AI Foundry docs: What's new for March 2025"
-description: "What's new in the Azure AI Foundry docs for March 2025."
+title: "Azure AI Foundry docs: What's new for April 2025"
+description: "What's new in the Azure AI Foundry docs for April 2025."
 ms.author: smcdowell
 author: skpmcdowell
 ms.topic: whats-new
 ms.subject: ai-studio
-ms.custom: March-2025
-ms.date: 04/02/2025
+ms.custom: April-2025
+ms.date: 05/03/2025
 ---
 
-# Azure AI Foundry docs: What's new for March 2025
+# Azure AI Foundry docs: What's new for April 2025
 
-Welcome to what's new in the Azure AI Foundry docs for March 2025. This article lists some of the major changes to docs during this period.
+Welcome to what's new in the Azure AI Foundry docs for April 2025. This article lists some of the major changes to docs during this period.
 
 
 ## Azure AI Foundry
 
 ### New articles
 
-- [Featured models of Azure AI Foundry](../ai-foundry/concepts/models-featured.md)
-- [How to deploy NVIDIA Inference Microservices](../ai-foundry/how-to/deploy-nvidia-inference-microservice.md)
-- [How to use image and audio in chat completions with Azure AI model inference](../ai-foundry/model-inference/how-to/use-chat-multi-modal.md)
-- [Tutorial: Get started with DeepSeek-R1 reasoning model in Azure AI model inference](../ai-foundry/model-inference/tutorials/get-started-deepseek-r1.md)
+- [AI Red Teaming Agent (preview)](../ai-foundry/concepts/ai-red-teaming-agent.md)
+- [Evaluate your AI agents locally with Azure AI Evaluation SDK (preview)](../ai-foundry/how-to/develop/agent-evaluate-sdk.md)
+- [How to use structured outputs for chat models](../ai-foundry/model-inference/how-to/use-structured-outputs.md)
+- [Run automated safety scans with AI Red Teaming Agent (preview)](../ai-foundry/how-to/develop/run-scans-ai-red-teaming-agent.md)
+- [Work with Azure AI Agent Service in Visual Studio Code (Preview)](../ai-foundry/how-to/develop/vs-code-agents.md)
+- [Work with the Azure AI Foundry for Visual Studio Code extension (Preview)](../ai-foundry/how-to/develop/get-started-projects-vs-code.md)
 
 
 ### Updated articles
 
-- [Deploy a flow for real-time inference](../ai-foundry/how-to/flow-deploy.md)
-- [Fine-tune models using serverless APIs in Azure AI Foundry](../ai-foundry/how-to/fine-tune-serverless.md)
-- [How to deploy and inference a managed compute deployment with code](../ai-foundry/how-to/deploy-models-managed.md) 
-- [How to trace your application with Azure AI Foundry project library](../ai-foundry/how-to/develop/trace-local-sdk.md) 
-- [Monitor quality and token usage of deployed prompt flow applications](../ai-foundry/how-to/monitor-quality-safety.md)
+- [Evaluate your AI agents locally with Azure AI Evaluation SDK (preview)](../ai-foundry/how-to/develop/agent-evaluate-sdk.md)  
+- [Evaluate your Generative AI application locally with the Azure AI Evaluation SDK](../ai-foundry/how-to/develop/evaluate-sdk.md) 
+- [Evaluation and monitoring metrics for generative AI](../ai-foundry/concepts/evaluation-metrics-built-in.md)  
+- [Fine-tune models using serverless APIs in Azure AI Foundry](../ai-foundry/how-to/fine-tune-serverless.md) 
+- [How to configure a private link for Azure AI Foundry hubs](../ai-foundry/how-to/configure-private-link.md) 
+- [How to use MedImageParse healthcare AI models for segmentation of medical images](../ai-foundry/how-to/healthcare-ai/deploy-medimageparse.md)
 
 
 

articles/ai-services/openai/how-to/realtime-audio.md

@@ -53,7 +53,7 @@ Often, the first event sent by the caller on a newly established `/realtime` ses
 
 The [`session.update`](../realtime-audio-reference.md#realtimeclienteventsessionupdate) event can be used to configure the following aspects of the session:
 - Transcription of user input audio is opted into via the session's `input_audio_transcription` property. Specifying a transcription model (such as `whisper-1`) in this configuration enables the delivery of [`conversation.item.audio_transcription.completed`](../realtime-audio-reference.md#realtimeservereventconversationiteminputaudiotranscriptioncompleted) events.
-- Turn handling is controlled by the `turn_detection` property. This property's type can be set to `none` or `server_vad` as described in the [voice activity detection (VAD) and the audio buffer](#voice-activity-detection-vad-and-the-audio-buffer) section.
+- Turn handling is controlled by the `turn_detection` property. This property's type can be set to `none`, `semantic_vad`, or `server_vad` as described in the [voice activity detection (VAD) and the audio buffer](#voice-activity-detection-vad-and-the-audio-buffer) section.
 - Tools can be configured to enable the server to call out to external services or functions to enrich the conversation. Tools are defined as part of the `tools` property in the session configuration.
 
 An example `session.update` that configures several aspects of the session, including tools, follows. All session parameters are optional and can be omitted if not needed.
@@ -144,9 +144,12 @@ You can also construct a custom context that the model uses outside of the sessi
 
 The server maintains an input audio buffer containing client-provided audio that hasn't yet been committed to the conversation state.
 
-One of the key [session-wide](#session-configuration) settings is `turn_detection`, which controls how data flow is handled between the caller and model. The `turn_detection` setting can be set to `none` or `server_vad` (to use [server-side voice activity detection](#server-decision-mode)).
+One of the key [session-wide](#session-configuration) settings is `turn_detection`, which controls how data flow is handled between the caller and model. The `turn_detection` setting can be set to `none`, `semantic_vad`, or `server_vad` (to use [server-side voice activity detection](#server-decision-mode)).
 
-By default, voice activity detection (VAD) is enabled, and the server automatically generates responses when it detects the end of speech in the input audio buffer. You can change the behavior by setting the `turn_detection` property in the session configuration.
+- `server_vad`: Automatically chunks the audio based on periods of silence.
+- `semantic_vad`: Chunks the audio when the model believes based on the words said by the user that they have completed their utterance.
+
+By default, server VAD (`server_vad`) is enabled, and the server automatically generates responses when it detects the end of speech in the input audio buffer. You can change the behavior by setting the `turn_detection` property in the session configuration.
 
 ### Without server decision mode
 
@@ -201,6 +204,12 @@ sequenceDiagram
     Server->>Client: conversation.item.created
 -->
 
+### Semantic VAD
+
+Semantic VAD detects when the user has finished speaking based on the words they have uttered. The input audio is scored based on the probability that the user is done speaking. When the probability is low the model will wait for a timeout. When the probability is high there's no need to wait. 
+
+With the (`semantic_vad`) mode, the model is less likely to interrupt the user during a speech-to-speech conversation, or chunk a transcript before the user is done speaking.
+
 ### VAD without automatic response generation
 
 You can use server-side voice activity detection (VAD) without automatic response generation. This approach can be useful when you want to implement some degree of moderation.