Merge pull request #5954 from MicrosoftDocs/main

Auto Publish – main to live - 2025-07-10 05:06 UTC

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

articles/ai-foundry/agents/how-to/tools/model-context-protocol.md

@@ -43,7 +43,7 @@ You can bring multiple remote MCP servers to Foundry Agent service by adding the
 1. Find the remote MCP server you want to connect to, such as GitHub MCP Server. Create or update a Foundry Agent with a `mcp` tool with the following information:
    1. `server_url`: the url of the MCP server, for example, `https://api.githubcopilot.com/mcp/`
    2. `server_label`: a unique identifier of this MCP server to the agent, for example, `github`
-   3. `allowed_tools`: optional, a list of tools you want to allow without approval
+   3. `allowed_tools`: optional, specify the tools that this agent can have access to and use.
 
 1. Create a run and pass additional information about the `mcp` tool in `tool_resources` with headers
    1. `tool_label`: use the identifier you provided during create/update agent

articles/ai-services/document-intelligence/concept/markdown-elements.md

@@ -108,6 +108,9 @@ The Layout API preserves figure elements:
 * Preserves figure captions with the `<figcaption>` tag to provide important context
 * Preserves figure footnotes as separate paragraphs following the figure container
 
+> [!IMPORTANT]
+> In cases where we detect certain document components like section heading as part of the figures, markdown output will not present figures in the output and use the information for document structure analysis. For these cases, enumerate the figures field in JSON to retrieve all the figures.
+
 Here's an example:
 
 ``` md 

articles/ai-services/document-intelligence/containers/configuration.md

@@ -16,7 +16,7 @@ ms.author: lajanuar
 
 :::moniker range="doc-intel-2.1.0"
 
-Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models, `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models, and `2024-11-30 (GA)` for Layout model:
+Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models, `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models, and `2024-11-30 (GA)` for Read and Layout model:
 
 * [REST API `2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
 * [REST API `2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
@@ -38,7 +38,7 @@ With Document Intelligence containers, you can build an application architecture
 
 > [!IMPORTANT]
 >
-> Document Intelligence v4.0 container is currently available for Layout model only.
+> Document Intelligence v4.0 container is currently available for Read and Layout model only.
 
 ## Configuration settings
 

articles/ai-services/document-intelligence/containers/image-tags.md

@@ -16,7 +16,7 @@ ms.author: lajanuar
 
 :::moniker range="doc-intel-2.1.0"
 
-Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models, `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models, and `2024-11-30 (GA)` for Layout model:
+Support for containers is currently available with Document Intelligence version `2022-08-31 (GA)` for all models, `2023-07-31 (GA)` for Read, Layout, Invoice, Receipt, and ID Document models, and `2024-11-30 (GA)` for Read and Layout model:
 
 * [REST API `2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
 * [REST API `2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
@@ -81,11 +81,12 @@ The following containers support DocumentIntelligence v3.1 models and features:
 
 Document Intelligence container images can be found within the [**Microsoft Artifact Registry** (also know as Microsoft Container Registry(MCR))](https://mcr.microsoft.com/catalog?search=document%20intelligence), the primary registry for all Microsoft published container images.
 
-The following containers support DocumentIntelligence v3.1 models and features:
+The following containers support Document Intelligence v4.0 models and features:
 
 | Container name |image |
 |---|---|
 | [**Layout 4.0**](https://mcr.microsoft.com/en-us/product/azure-cognitive-services/form-recognizer/layout-4.0/tags) |`mcr.microsoft.com/azure-cognitive-services/form-recognizer/layout-4.0:latest`|
+| [**Read 4.0**](https://mcr.microsoft.com/product/azure-cognitive-services/form-recognizer/read-4.0/tags) |`mcr.microsoft.com/azure-cognitive-services/form-recognizer/read-4.0:latest`|
 ::: moniker-end
 
 

articles/ai-services/document-intelligence/containers/install-run.md

@@ -23,15 +23,15 @@ Azure AI Document Intelligence is an Azure AI service that lets you build automa
 
 In this article you can learn how to download, install, and run Document Intelligence containers. Containers enable you to run the Document Intelligence service in your own environment. Containers are great for specific security and data governance requirements.
 
-* **Layout** model is supported by Document Intelligence v4.0 containers.
+* **Read**, **Layout** model is supported by Document Intelligence v4.0 containers.
 
 * **Read**, **Layout**,  **ID Document**,  **Receipt**, and **Invoice**  models are supported by Document Intelligence v3.1 containers.
 
 * **Read**, **Layout**, **General Document**, **Business Card**, and **Custom** models are supported by Document Intelligence v3.0 containers.
 
 ## Version support
 
-Support for containers is currently available with Document Intelligence version `v3.0: 2022-08-31 (GA)` for all models, `v3.1 2023-07-31 (GA)` for Read, Layout, ID Document, Receipt, and Invoice models, and `v4.0 2024-11-30 (GA)` for Layout:
+Support for containers is currently available with Document Intelligence version `v3.0: 2022-08-31 (GA)` for all models, `v3.1 2023-07-31 (GA)` for Read, Layout, ID Document, Receipt, and Invoice models, and `v4.0 2024-11-30 (GA)` for Read and Layout:
 
 * [REST API `v3.0: 2022-08-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.0%20(2022-08-31)&preserve-view=true&tabs=HTTP)
 * [REST API `v3.1: 2023-07-31 (GA)`](/rest/api/aiservices/document-models/analyze-document?view=rest-aiservices-v3.1%20(2023-07-31)&tabs=HTTP&preserve-view=true)
@@ -171,7 +171,7 @@ version: "3.9"
 services:
   azure-form-recognizer-read:
     container_name: azure-form-recognizer-read
-    image: mcr.microsoft.com/azure-cognitive-services/form-recognizer/read-3.1
+    image: mcr.microsoft.com/azure-cognitive-services/form-recognizer/read-4.0
     environment:
       - EULA=accept
       - billing={FORM_RECOGNIZER_ENDPOINT_URI}

articles/ai-services/document-intelligence/whats-new.md

@@ -27,8 +27,15 @@ Document Intelligence service is updated on an ongoing basis. Bookmark this page
 > [!IMPORTANT]
 > Preview API versions are retired once the GA API is released. The 2023-02-28-preview API version is retiring. If you're still using the preview API or the associated SDK versions, update your code to target the latest API version `2024-11-30 (GA)`. </br>
 
+## June 2025
+**Document Intelligence v4.0 Read container is now available!**
+<br>
+This container image includes highly requested Read features like searchable PDF! For more information, *see:*
+* [Install and run containers](containers/install-run.md?view=doc-intel-4.0.0&preserve-view=true)
+* [Container image tags](containers/image-tags.md?view=doc-intel-4.0.0&preserve-view=true)
+
 ## April 2025
-**Document Intelligence v4.0 container is now available! Currently, Layout model is the only supported model for v4.0 release.**
+**Document Intelligence v4.0 Layout container is now available!**
 <br>
 For more information, *see:*
 * [Install and run containers](containers/install-run.md?view=doc-intel-4.0.0&preserve-view=true)

articles/ai-services/speech-service/speech-synthesis-markup-voice.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 3/10/2025
+ms.date: 7/9/2025
 ms.author: eur
 ms.custom: references_regions
 #Customer intent: As a developer, I want to learn how to use Speech Synthesis Markup Language (SSML) elements to customize what my Speech service voice sounds like.
@@ -559,9 +559,9 @@ This SSML snippet illustrates how to request blend shapes with your synthesized
 
 ## Voice conversion element
 
-Voice conversion is the process of transforming the voice characteristics of a given audio to a target voice speaker. After voice conversion, the resulting audio reserves source audio's linguistic content and prosody while the voice timbre sounds like the target speaker. For more information, see [voice conversion](./voice-conversion.md).
+Voice conversion (preview) is the process of transforming the voice characteristics of a given audio to a target voice speaker. After voice conversion, the resulting audio reserves source audio's linguistic content and prosody while the voice timbre sounds like the target speaker. For more information, see [voice conversion](./voice-conversion.md).
 
-Use the `<mstts:voiceconversion>` tag via Speech Synthesis Markup Language (SSML) to specify the source audio URL and the target voice for the conversion. For a complete list of supported target voices, see [supported voices for voice conversion](./language-support.md#voice-conversion).
+Use the `<mstts:voiceconversion>` tag via Speech Synthesis Markup Language (SSML) to specify the source audio URL and the target voice for the conversion. For a complete list of supported target voices, see [supported voices for voice conversion](./language-support.md?tabs=tts#voice-conversion).
 
 The following table describes the usage of the `mstts:voiceconversion` element's attributes:
 
@@ -573,7 +573,7 @@ Here's how the voice conversion works:
 - The source audio is a prerecorded audio file that contains the spoken words and prosody.
   - Text content: The final synthesized speech follows the spoken words in the source audio.
   - Prosody and rhythm: The speech maintains the timing and intonation from the source.
-- The `<voice>` tag specifies the target voice used for the output audio. For information about the supported target voices, see [supported voices for voice conversion](./language-support.md#voice-conversion).
+- The `<voice>` tag specifies the target voice used for the output audio. For information about the supported target voices, see [supported voices for voice conversion](./language-support.md?tabs=tts#voice-conversion).
 - The output audio keeps the timbre (tone and voice quality) of the target voice, but follows the text and speaking style of the source audio.
 
 > [!NOTE]

articles/ai-services/speech-service/toc.yml

@@ -136,7 +136,7 @@ items:
     - name: High definition (HD) voices
       href: high-definition-voices.md
       displayName: hd voice
-    - name: Voice conversion
+    - name: Voice conversion (preview)
       href: voice-conversion.md
       displayName: voice conversion
     - name: Custom voice

articles/ai-services/speech-service/voice-conversion.md

@@ -8,11 +8,13 @@ ms.reviewer: eur
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: overview
-ms.date: 7/1/2025
+ms.date: 7/9/2025
 ms.custom: references_regions
 ---
 
-# What is voice conversion?
+# What is voice conversion? (Preview)
+
+[!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
 
 Voice conversion is the process of transforming the voice characteristics of a given audio to a target voice speaker. After voice conversion, the resulting audio reserves source audio's linguistic content and prosody while the voice timbre sounds like the target speaker.
 
@@ -31,13 +33,13 @@ Voice conversion (or voice changer or speech to speech conversion) is built on s
 | **High speaker similarity**   | Captures the timbre and vocal identity of the target speaker.<br>Generates audio that accurately matches the target voice. |
 | **Prosody preservation**      | Maintains rhythm, stress, and intonation of source audio.<br>Preserves expressive and emotional qualities. |
 | **High audio fidelity**       | Generates realistic, natural-sounding audio.<br>Minimizes artifacts.                                      |
-| **Multilingual support**      | Enables multilingual voice conversion.<br>Supports 91 locales (same as standard text to speech locale support).<br>See [supported voices for voice conversion](./language-support.md#voice-conversion) for the complete list. |
+| **Multilingual support**      | Enables multilingual voice conversion.<br>Supports 91 locales (same as standard text to speech locale support).<br>See [supported voices for voice conversion](./language-support.md?tabs=tts#voice-conversion) for the complete list. |
 
 ## Use voice conversion
 
 You can use Azure AI Speech voice conversion with either the Speech SDK or text to speech REST APIs.
 
-Use the `<mstts:voiceconversion>` tag via Speech Synthesis Markup Language (SSML) to specify the source audio URL and the target voice for the conversion. For a complete list of supported target voices, see [supported voices for voice conversion](./language-support.md#voice-conversion).
+Use the `<mstts:voiceconversion>` tag via Speech Synthesis Markup Language (SSML) to specify the source audio URL and the target voice for the conversion. For a complete list of supported target voices, see [supported voices for voice conversion](./language-support.md?tabs=tts#voice-conversion).
 
 ### Example SSML
 

articles/search/cognitive-search-skill-document-intelligence-layout.md

@@ -11,14 +11,14 @@ ms.custom:
   - references_regions
   - ignite-2024
 ms.topic: reference
-ms.date: 06/10/2025
+ms.date: 07/10/2025
 ---
 
 # Document Layout skill
 
 [!INCLUDE [Feature preview](./includes/previews/preview-generic.md)]
 
-The **Document Layout** skill analyzes a document to detect structure and characteristics, and produces a syntactical representation of the document in Markdown or Text format. You can use it to extract text and images, where image extraction includes location metadata that preserves image position within the document. Image proximity to related content adds value to Retrieval Augmented Generation (RAG) workloads and [multimodal search](multimodal-search-overview.md).
+The **Document Layout** skill analyzes a document to detect structure and characteristics, and produces a syntactical representation of the document in Markdown or Text format. You can use it to extract text and images, where image extraction includes location metadata that preserves image position within the document. Image proximity to related content is beneficial in Retrieval Augmented Generation (RAG) workloads and [multimodal search](multimodal-search-overview.md) scenarios.
 
 This article is the reference documentation for the Document Layout skill. For usage information, see [How to chunk and vectorize by document layout](search-how-to-semantic-chunking.md). 
 
@@ -46,11 +46,11 @@ The Document Layout skill calls the [Document Intelligence Public preview versio
 
 Supported regions vary by modality and how the skill connects to the Document Intelligence layout model.
 
-| Approach | Regions | Requirement |
-|----------|---------|-------------|
-| [Import and vectorize data wizard](search-import-data-portal.md) | **East US**, **West Europe**, **North Central US** | Create an Azure AI multi-service resource in one of these regions to get the portal experience. |
-| Programmatic, using a [keyless connection (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) for billing | Varies by resource | Create Azure AI Search in one of these regions:  **East US**, **West Europe**, **North Central US**, **West US 2**. <br>Access Document Intelligence through an Azure AI multi-service resource in any region listed in the [Product availability by region](https://azure.microsoft.com/explore/global-infrastructure/products-by-region/table) table.|
-| Programmatic, using a [multi-service resource API key](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) for billing | **East US**, **West Europe**, **North Central US**, **West US 2** | Create your Azure AI Search service and AI multi-service resource in the same region. |
+| Approach | Requirement |
+|----------|-------------|
+| [Import and vectorize data wizard](search-import-data-portal.md) | Create an Azure AI multi-service resource in one of these regions to get the portal experience: **East US**, **West Europe**, **North Central US**. | 
+| Programmatic, using [Microsoft Entra ID authentication (preview)](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) for billing |  Create Azure AI Search in one of these regions:  **East US**, **West Europe**, **North Central US**, **West US 2**. <br>Create the Azure AI multi-service resource in any region listed in the [Product availability by region](https://azure.microsoft.com/explore/global-infrastructure/products-by-region/table) table.|
+| Programmatic, using a [multi-service resource API key](cognitive-search-attach-cognitive-services.md#bill-through-a-keyless-connection) for billing | Create your Azure AI Search service and AI multi-service resource in the same region: **East US**, **West Europe**, **North Central US**, **West US 2**. |
 
 ## Supported file formats