Merge branch 'main' of github.com:MicrosoftDocs/azure-ai-docs-pr into sdg-update-links

Author: sdgilley

articles/ai-foundry/foundry-models/includes/models-azure-direct-others.md

@@ -27,9 +27,10 @@ The DeepSeek family of models includes DeepSeek-R1, which excels at reasoning ta
 
 | Model  | Type | Capabilities | Deployment type (region availability) | Project type |
 | ------ | ---- | ------------ | ------------------------------------- | ------------ |
-| [DeepSeek-R1-0528](https://ai.azure.com/explore/models/deepseek-r1-0528/version/1/registry/azureml-deepseek/?cid=learnDocs) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. | - Global standard (all regions) <br> - Global provisioned (all regions)| Foundry, Hub-based |
-| [DeepSeek-V3-0324](https://ai.azure.com/explore/models/deepseek-v3-0324/version/1/registry/azureml-deepseek/?cid=learnDocs) | chat-completion | - **Input:** text (131,072 tokens) <br /> - **Output:**  (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON | - Global standard (all regions) <br> - Global provisioned (all regions) | Foundry, Hub-based |
-| [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek/?cid=learnDocs) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. | - Global standard (all regions) <br> - Global provisioned (all regions) | Foundry, Hub-based |
+| [DeepSeek-V3.1](https://ai.azure.com/resource/models/DeepSeek-V3.1/version/1/registry/azureml-deepseek?cid=learnDocs) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | - **Input:** text (131,072 tokens) <br /> - **Output:**  (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON | - Global standard (all regions) <br> - Global provisioned (all regions) | Foundry, Hub-based |
+| [DeepSeek-R1-0528](https://ai.azure.com/explore/models/deepseek-r1-0528/version/1/registry/azureml-deepseek?cid=learnDocs) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. | - Global standard (all regions) <br> - Global provisioned (all regions)| Foundry, Hub-based |
+| [DeepSeek-V3-0324](https://ai.azure.com/explore/models/deepseek-v3-0324/version/1/registry/azureml-deepseek?cid=learnDocs) | chat-completion | - **Input:** text (131,072 tokens) <br /> - **Output:**  (131,072 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** Yes <br /> - **Response formats:** Text, JSON | - Global standard (all regions) <br> - Global provisioned (all regions) | Foundry, Hub-based |
+| [DeepSeek-R1](https://ai.azure.com/explore/models/deepseek-r1/version/1/registry/azureml-deepseek?cid=learnDocs) | chat-completion <br /> [(with reasoning content)](../how-to/use-chat-reasoning.md) | - **Input:** text (163,840 tokens) <br /> - **Output:**  (163,840 tokens) <br /> - **Languages:** `en` and `zh` <br />  - **Tool calling:** No <br /> - **Response formats:** Text. | - Global standard (all regions) <br> - Global provisioned (all regions) | Foundry, Hub-based |
 
 See [this model collection in Azure AI Foundry portal](https://ai.azure.com/explore/models?&selectedCollection=DeepSeek/?cid=learnDocs).
 

articles/ai-foundry/how-to/upgrade-azure-openai.md

@@ -44,6 +44,7 @@ Your existing resource configurations and state remain preserved including:
 Backend limitations:
 
 * Azure OpenAI resources using **customer-managed keys** for encryption aren't supported for upgrade.
+* [Modified Abuse Monitoring](../responsible-ai/openai/data-privacy.md?tabs=azure-portal#prerequisites) isn't supported on Azure AI Foundry resource.
 * The AI Foundry resource type doesn't support configuring Weights & Biases.
 
 Foundry portal limitations:

articles/ai-foundry/openai/how-to/content-filters.md

@@ -22,7 +22,7 @@ The default content filtering configuration is set to filter at the medium sever
 Prompt shields and protected text and code models are optional and on by default. For prompt shields and protected material text and code models, the configurability feature allows all customers to turn the models on and off. The models are by default on and can be turned off per your scenario. Some models are required to be on for certain scenarios to retain coverage under the [Customer Copyright Commitment](/azure/ai-foundry/responsible-ai/openai/customer-copyright-commitment).
 
 > [!NOTE]
-> All customers have the ability to modify the content filters and configure the severity thresholds (low, medium, high). Approval is required for turning the content filters partially or fully off. Managed customers only may apply for full content filtering control via this form: [Azure OpenAI Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR). At this time, it is not possible to become a managed customer.
+> All customers have the ability to modify the content filters and configure the severity thresholds (low, medium, high). Approval is required for turning the content filters partially or fully off. Managed customers only may apply for full content filtering control via this form: [Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR). At this time, it is not possible to become a managed customer.
 
 > [!IMPORTANT]
 > The GPT-image-1 model does not support content filtering configuration: only the default content filter is used.

articles/ai-foundry/openai/how-to/dall-e.md

@@ -71,8 +71,6 @@ The following is a sample request body. You specify a number of options, defined
 }
 ```
 
-
-
 #### [DALL-E 3](#tab/dalle-3)
 
 Send a POST request to:
@@ -147,8 +145,46 @@ The response from a successful image generation API call looks like the followin
     ]
 } 
 ```
+
 ---
 
+### Streaming
+
+You can stream image generation requests to `gpt-image-1` by setting the `stream` parameter to `true`, and setting the `partial_images` parameter to a value between 0 and 3.
+
+```python
+from openai import OpenAI
+from azure.identity import DefaultAzureCredential, get_bearer_token_provider
+
+token_provider = get_bearer_token_provider(
+    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
+)
+
+client = OpenAI(  
+  base_url = "https://RESOURCE-NAME-HERE/openai/v1/",  
+  api_key=token_provider,
+  default_headers={"x-ms-oai-image-generation-deployment":"gpt-image-1", "api_version":"preview"}
+)
+
+stream = client.images.generate(
+    model="gpt-image-1",
+    prompt="A cute baby sea otter",
+    n=1,
+    size="1024x1024",
+    stream=True,
+    partial_images = 2
+)
+
+for event in stream:
+    if event.type == "image_generation.partial_image":
+        idx = event.partial_image_index
+        image_base64 = event.b64_json
+        image_bytes = base64.b64decode(image_base64)
+        with open(f"river{idx}.png", "wb") as f:
+            f.write(image_bytes)
+ 
+```
+
 
 ### API call rejection
 

articles/ai-foundry/openai/how-to/responses.md

@@ -1265,14 +1265,9 @@ Compared to the standalone Image API, the Responses API offers several advantage
 * **Flexible inputs**: Accept image File IDs as inputs, in addition to raw image bytes.
 
 > [!NOTE]
-> The image generation tool in the Responses API is only supported by the `gpt-image-1` model. You can however call this model from this list of supported models - `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `o3`.
+> The image generation tool in the Responses API is only supported by the `gpt-image-1` model. You can however call this model from this list of supported models - `gpt-4o`, `gpt-4o-mini`, `gpt-4.1`, `gpt-4.1-mini`, `gpt-4.1-nano`, `o3`, and `gpt-5` series models.<br><br>The Responses API image generation tool does not currently support streaming mode. To use streaming mode and generate partial images, call the [image generation API](./dall-e.md) directly outside of the Responses API.
 
-Use the Responses API if you want to:
-
-* Build conversational image experiences with GPT Image.
-* Stream partial image results during generation for a smoother user experience.
-
-Generate an image
+Use the Responses API if you want to build conversational image experiences with GPT Image.
 
 
 ```python
@@ -1309,41 +1304,6 @@ if image_data:
         f.write(base64.b64decode(image_base64))
 ```
 
-### Streaming
-
-You can stream partial images using Responses API. The `partial_images` can be used to receive 1-3 partial images
-
-```python
-from openai import AzureOpenAI
-from azure.identity import DefaultAzureCredential, get_bearer_token_provider
-
-token_provider = get_bearer_token_provider(
-    DefaultAzureCredential(), "https://cognitiveservices.azure.com/.default"
-)
-
-client = AzureOpenAI(  
-  base_url = "https://YOUR-RESOURCE-NAME.openai.azure.com/openai/v1/",  
-  azure_ad_token_provider=token_provider,
-  api_version="preview",
-  default_headers={"x-ms-oai-image-generation-deployment":"YOUR-GPT-IMAGE1-DEPLOYMENT-NAME"}
-)
-
-stream = client.responses.create(
-    model="gpt-4.1",
-    input="Draw a gorgeous image of a river made of white owl feathers, snaking its way through a serene winter landscape",
-    stream=True,
-    tools=[{"type": "image_generation", "partial_images": 2}],
-)
-
-for event in stream:
-    if event.type == "response.image_generation_call.partial_image":
-        idx = event.partial_image_index
-        image_base64 = event.partial_image_b64
-        image_bytes = base64.b64decode(image_base64)
-        with open(f"river{idx}.png", "wb") as f:
-            f.write(image_bytes)
-```
-
 ## Reasoning models
 
 For examples of how to use reasoning models with the responses API see the [reasoning models guide](./reasoning.md#reasoning-summary).

articles/ai-foundry/openai/includes/content-filter-configurability.md

@@ -23,7 +23,7 @@ All customers can also configure content filters and create custom content polic
 | No filters | If approved<sup>1</sup>| If approved<sup>1</sup>| No content is filtered regardless of severity level detected. Requires approval<sup>1</sup>.|
 |Annotate only | If approved<sup>1</sup>| If approved<sup>1</sup>| Disables the filter functionality, so content will not be blocked, but annotations are returned via API response. Requires approval<sup>1</sup>.|
 
-<sup>1</sup> For Azure OpenAI models, only customers who have been approved for modified content filtering have full content filtering control and can turn off content filters. Apply for modified content filters via this form: [Azure OpenAI Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR). For Azure Government customers, apply for modified content filters via this form: [Azure Government - Request Modified Content Filtering for Azure OpenAI](https://aka.ms/AOAIGovModifyContentFilter).
+<sup>1</sup> For Azure OpenAI models, only customers who have been approved for modified content filtering have full content filtering control and can turn off content filters. Apply for modified content filters via this form: [Limited Access Review: Modified Content Filters](https://ncv.microsoft.com/uEfCgnITdR). For Azure Government customers, apply for modified content filters via this form: [Azure Government - Request Modified Content Filtering](https://aka.ms/AOAIGovModifyContentFilter).
 
 Configurable content filters for inputs (prompts) and outputs (completions) are available for all Azure OpenAI models.
 

articles/ai-foundry/responsible-ai/speech-service/text-to-speech/transparency-note.md

@@ -99,13 +99,13 @@ In addition to the common terms from prebuilt neural voice, custom neural voice,
 |---|---|
 | Avatar talent | Custom text to speech avatar model building requires training on a video recording of a real human speaking. This person is the avatar talent. Customers must get sufficient consent under all relevant laws and regulations from the avatar talent to use their image/likeness to create a custom avatar. |
 
-#### [Video translation (preview)](#tab/video)
+#### [Video translation](#tab/video)
 
 ### Introduction
 
 Video translation can efficiently localize your video content to cater to diverse audiences around the globe. This service empowers you to create immersive, localized content efficiently and effectively across various use cases such as vlogs, education, news, advertising, and more.
 
-Video translation using prebuilt neural voices is available in preview for all users. Video translation with personal voice is a Limited Access feature in preview and is subject to use case and eligibility restrictions.
+Video translation using prebuilt neural voices is available for all users.
 
 ### Key terms
 
@@ -169,7 +169,7 @@ Text to speech avatar adopts Coalition for Content Provenance and Authenticity (
 In addition, avatar outputs are automatically watermarked. Watermarks allow approved users to identify whether a video is synthesized using the avatar feature of Azure AI Speech.  To request watermark detection, please contact [avatarvoice[at]microsoft.com](mailto:[email protected]).
 
 
-### Video translation (preview)
+### Video translation
 
 Video translation can efficiently localize your video content to cater to diverse audiences around the globe. Video translation will automatically extract dialogue audio, transcribe, translate and dub the content with prebuilt or personal voice to the target language, with accurate subtitles for better accessibility. Multi-speaker features will help identify the number of individuals speaking and recommend suitable voices. Content editing with human in the loop allows for precise alignment with customer preference. Enhanced translation quality ensures precise audio and video alignment with GPT integration. Video translation enables authentic and personalized dubbing experiences with personal voice.
 
@@ -209,7 +209,7 @@ All other uses of custom neural voice, including Custom Neural Voice Pro, Custom
 
 Prebuilt neural voice may also be used for the custom neural voice use cases above, as well as additional use cases selected by customers and consistent with the Azure Acceptable Use Policy and the [Code of conduct for Azure AI Speech text to speech](/legal/ai-code-of-conduct?context=%2Fazure%2Fai-services%2Fspeech-service%2Fcontext%2Fcontext). No registration or pre-approval is required for additional use cases for prebuilt neural voice that meet all applicable terms and conditions. 
 
-### Intended use cases for video translation (preview)
+### Intended use cases for video translation
 
 Video translation could be used for films, TV, and other visual (including but not limited to video or animation) and audio applications, where customers maintain sole control over the creation of, access to, and use of the voice models and their output. Personal voice and lip syncing are subject to the Limited Access framework, and eligible customers may use these capabilities with Video translation. The following are the approved use cases for Video translation service:
 - **Education & learning**: To translate audio in educational visuals, online courses, training modules, simulation-based learning, or guided museum tour visuals for multilingual learners.  
@@ -301,7 +301,7 @@ Technical limitations to consider are the accuracy of lip sync alignment with th
 - **Gestures**: Avatars may use hand gestures during speaking to deliver a natural speaking experience, but the gestures are not pre-programmed. Instead, they are learned from video clips in the training data and are included in synthetic video regardless of the input text. Also, avatars cannot make gestures that were not made by the avatar talent and captured in the training data. Avatars are not able to tailor gestures according to contextual information and emotions, so customers should be mindful of the avatar system’s inability to automatically play a gesture appropriate for the context.  
 - **Privacy and data protection**: When utilizing text to speech avatars, customers should adhere to all applicable privacy laws and regulations and ensure that sensitive or personal information is handled securely. It is important to be cautious when processing and storing data, and to follow best practices for data protection and consent management.
 
-#### [Video translation (preview)](#tab/video)
+#### [Video translation](#tab/video)
 
 * **Translation quality**: Translation quality will depend on the transcription accuracy and translation accuracy. If the input video is mixed with background music or noise, this will impact the quality of the translation. Translation results will be dependent on context.
 * **Dubbing voice similarity and intonation**: When you choose prebuilt neural voices for dubbing, the voice output characteristics may not be similar to the original voice characteristics. If you use the personal voice feature, the voice output will more closely resemble the original voice, but the speaking style may not closely resemble the user’s speaking style including tones and prosodies. It’s also possible the voice output will not sound equally natural across all supported languages. 
@@ -395,7 +395,7 @@ The quality of the resulting avatar heavily depends on the recorded video used f
 
 The appearance and performance of the avatar talent are also key factors impacting the system performance; please see our guidance [How to record video samples for custom text to speech avatar](/azure/ai-services/speech-service/text-to-speech-avatar/custom-avatar-record-video-samples).
 
-#### [Video translation (preview)](#tab/video)
+#### [Video translation](#tab/video)
 ---
 
 ## Evaluation of text to speech  

articles/ai-foundry/what-is-azure-ai-foundry.md

@@ -82,10 +82,11 @@ This table summarizes features available in the two project types:
 | Models sold directly by Azure - Azure OpenAI, DeepSeek, xAI, etc. | ✅ | Available via connections |
 | Partner & Community Models sold through Marketplace - Stability, Bria, Cohere, etc. | ✅ | Available via connections |
 | Open source models such as HuggingFace  |  | ✅ |
-| Evaluations | ✅ | ✅ |
+| Evaluations | ✅ (preview) | ✅ |
 | Playground | ✅ | ✅ |
 | Prompt flow |  | ✅ |
 | Content understanding  | ✅ | ✅ |
+| Model router  | ✅ | ✅ |
 | Project files (directly upload files and start experimenting) | ✅ | |
 | Project-level isolation of files and outputs | ✅ | ✅|
 | Required Azure dependencies | - | Azure Storage account, Azure Key Vault |

articles/ai-services/speech-service/how-to-custom-speech-transcription-editor.md

@@ -2,17 +2,20 @@
 title: How to use the online transcription editor for custom speech - Speech service
 titleSuffix: Azure AI services
 description: The online transcription editor allows you to create or edit audio + human-labeled transcriptions for custom speech.
-author: PatrickFarley
+author: goergenj
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 5/19/2025
-ms.author: pafarley
+ms.date: 9/11/2025
+ms.author: jagoerge
 #Customer intent: As a developer, I need to understand how to use the online transcription editor for custom speech so that I can create or edit audio + human-labeled transcriptions for custom speech.
 ---
 
 # How to use the online transcription editor
 
+[!INCLUDE [deprecation notice](./includes/retire-online-transcription-editor.md)]
+
+
 The online transcription editor allows you to create or edit audio + human-labeled transcriptions for custom speech. The main use cases of the editor are as follows: 
 
 * You only have audio data, but want to build accurate audio + human-labeled datasets from scratch to use in model training.