Merge pull request #5089 from MicrosoftDocs/release-ai-speech-cnv-foundry

Release ai speech cnv foundry -> main -- 05/20 - 15:00

Author: Albertyang0

.openpublishing.redirection.json

@@ -289,6 +289,11 @@
       "source_path": "articles/ai-services/index.yml",
       "redirect_url": "/azure/ai-foundry",
       "redirect_document_id": false
+    },
+    {
+      "source_path_from_root": "/articles/ai-services/speech-service/text-to-speech-avatar/custom-avatar-endpoint.md",
+      "redirect_url": "/azure/ai-services/speech-service/custom-avatar-create",
+      "redirect_document_id": false
     }
   ]
 }

articles/ai-foundry/toc.yml

@@ -264,14 +264,20 @@ items:
       href: ../ai-services/speech-service/get-started-speech-to-text.md?context=/azure/ai-foundry/context/context
     - name: Fast transcription
       href: ../ai-services/speech-service/fast-transcription-create.md?context=/azure/ai-foundry/context/context
+    - name: Fine-tune your speech model
+      items:
+      - name: Custom speech fine-tuning
+        href: ../ai-services/speech-service/how-to-custom-speech-create-project.md?context=/azure/ai-foundry/context/context
+      - name: Custom voice fine-tuning
+        href: ../ai-services/speech-service/professional-voice-create-project.md?context=/azure/ai-foundry/context/context
+      - name: Custom avatar fine-tuning
+        href: ../ai-services/speech-service/text-to-speech-avatar/custom-avatar-create.md?context=/azure/ai-foundry/context/context
     - name: Pronunciation assessment
       href: ../ai-services/speech-service/pronunciation-assessment-tool.md?context=/azure/ai-foundry/context/context
     - name: Speech translation
       href: ../ai-services/speech-service/get-started-speech-translation.md?context=/azure/ai-foundry/context/context
     - name: Hear and speak with chat in the playground
       href: quickstarts/hear-speak-playground.md
-    - name: Custom speech fine-tuning
-      href: ../ai-services/speech-service/how-to-custom-speech-create-project.md?context=/azure/ai-foundry/context/context
   - name:  Translator
     items:
     - name: What is Azure AI Translator?

articles/ai-services/speech-service/batch-synthesis.md

@@ -42,7 +42,7 @@ For code samples, see [GitHub](https://github.com/Azure-Samples/cognitive-servic
 To submit a batch synthesis request, construct the HTTP PUT request path and body according to the following instructions:
 
 - Set the required `inputKind` property.
-- If the `inputKind` property is set to "PlainText", then you must also set the `voice` property in the `synthesisConfig`. In the example below, the `inputKind` is set to "SSML", so the `synthesisConfig` isn't set.
+- If the `inputKind` property is set to "PlainText", then you must also set the `voice` property in the `synthesisConfig`. In the following example, the `inputKind` is set to "SSML", so the `synthesisConfig` isn't set.
 - Optionally you can set the `description`, `timeToLiveInHours`, and other properties. For more information, see [batch synthesis properties](batch-synthesis-properties.md).
 
 > [!NOTE]

articles/ai-services/speech-service/high-definition-voices.md

@@ -37,8 +37,8 @@ Here's a comparison of features between Azure AI Speech HD voices, Azure OpenAI
 | Feature | Azure AI Speech HD voices  | Azure OpenAI HD voices | Azure AI Speech voices (not HD) |
 |---------|---------------|------------------------|------------------------|
 | **Region** | East US, Southeast Asia, West Europe | North Central US, Sweden Central | Available in dozens of regions. See the [region list](regions.md#regions).|
-| **Number of voices** | 12 | 6 | More than 500 |
-| **Multilingual**  | No (perform on primary language only) | Yes  | Yes (applicable only to multilingual voices)  |
+| **Number of voices** | 30 | 6 | More than 500 |
+| **Multilingual**  | Yes | Yes  | Yes (applicable only to multilingual voices)  |
 | **SSML support** | Support for [a subset of SSML elements](#supported-and-unsupported-ssml-elements-for-azure-ai-speech-hd-voices).|  Support for [a subset of SSML elements](openai-voices.md#ssml-elements-supported-by-openai-text-to-speech-voices-in-azure-ai-speech).  | Support for the [full set of SSML](speech-synthesis-markup-structure.md) in Azure AI Speech.  |
 | **Development options** | Speech SDK, Speech CLI, REST API  | Speech SDK, Speech CLI, REST API  | Speech SDK, Speech CLI, REST API  |
 | **Deployment options**  | Cloud only | Cloud only | Cloud, embedded, hybrid, and containers. |

articles/ai-services/speech-service/how-to-custom-speech-create-project.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio
 #Customer intent: As a developer, I want to learn how to customize speech models with fine-tuning so that I can train and deploy a custom model.
@@ -35,9 +35,9 @@ In the [Azure AI Foundry portal](https://ai.azure.com), you can fine-tune some A
 1. Select **Fine-tuning** from the left pane.
 1. Select **AI Service fine-tuning** > **+ Fine-tune**.
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/fine-tune-azure-ai-services.png" alt-text="Screenshot of the page to select fine-tuning of Azure AI Services models." lightbox="./media/ai-foundry/custom-speech/fine-tune-azure-ai-services.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/fine-tune-azure-ai-services.png" alt-text="Screenshot of the page to select fine-tuning of Azure AI Services models." lightbox="./media/custom-speech/ai-foundry/fine-tune-azure-ai-services.png":::
 
-1. In the wizard, select **Speech to text (speech recognition)** for custom speech. Then select **Next**.
+1. In the wizard, select **Custom Speech (speech to text fine-tuning)** for custom speech. Then select **Next**.
 
 1. Enter the language, name, and description for the fine-tuning job. Then select **Create**.
 
@@ -49,6 +49,16 @@ Go to the Azure AI Speech documentation to learn how to continue fine-tuning you
 * [Test model quantitatively](how-to-custom-speech-evaluate-data.md) and [test model qualitatively](./how-to-custom-speech-inspect-data.md)
 * [Deploy a model](how-to-custom-speech-deploy-model.md)
 
+## View fine-tuned models
+
+After fine-tuning, you can access your custom speech models and deployments from the **Fine-tuning** page. 
+
+1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
+1. Select **Fine-tuning** from the left pane.
+1. Select **AI Service fine-tuning**.
+
+    :::image type="content" source="./media/custom-speech/ai-foundry/fine-tune-succeeded-list.png" alt-text="Screenshot of the page where you can view fine-tuned AI services models." lightbox="./media/custom-speech/ai-foundry/fine-tune-succeeded-list.png":::
+
 ::: zone-end
 
 ::: zone pivot="speech-studio"

articles/ai-services/speech-service/how-to-custom-speech-deploy-model.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 #Customer intent: As a developer, I want to learn how to deploy a custom speech model so that I can use it in my applications.
@@ -29,22 +29,21 @@ You can deploy an endpoint for a base or custom model, and then [update](#change
 ::: zone pivot="ai-foundry-portal"
 
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After you're satisfied with the test results, select **Deploy models** from the left menu. Then select **+ Deploy model**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Deploy models** > **+ Deploy models**. 
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-deploy-model.png" alt-text="Screenshot of the page with an option to deploy the custom speech model." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-deploy-model.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model.png" alt-text="Screenshot of the page with an option to deploy the custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model.png":::
 
 1. In the **Deploy a new model** wizard, select the model that you want to deploy. 
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-deploy-model-select-and-deploy.png" alt-text="Screenshot of the page with an option to select the model that you want to deploy." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-deploy-model-select-and-deploy.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model-select-and-deploy.png" alt-text="Screenshot of the page with an option to select the model that you want to deploy." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model-select-and-deploy.png":::
 
 1. Enter a name and description for the deployment. Select the box to agree to the terms of use. Then select **Deploy**.
 
 1. After the deployment status is **Succeeded**, you can view the deployment details. Select the deployment to view the details like the endpoint ID. 
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-deploy-model-status-succeeded.png" alt-text="Screenshot of the page with an option to select the deployment to view the details like the endpoint ID." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-deploy-model-status-succeeded.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model-status-succeeded.png" alt-text="Screenshot of the page with an option to select the deployment to view the details like the endpoint ID." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-deploy-model-status-succeeded.png":::
 
 
 ::: zone-end

articles/ai-services/speech-service/how-to-custom-speech-display-text-format.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 #Customer intent: As a developer, I want to learn how to prepare display text format training data for custom speech so that I can customize the display text formatting pipeline for my specific scenarios.
 ---

articles/ai-services/speech-service/how-to-custom-speech-evaluate-data.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 show_latex: true
@@ -24,29 +24,32 @@ In this article, you learn how to quantitatively measure and improve the accurac
 
 You can test the accuracy of your custom model by creating a test. A test requires a collection of audio files and their corresponding transcriptions. You can compare a custom model's accuracy with a speech to text base model or another custom model. After you [get](#get-test-results) the test results, [evaluate the word error rate (WER)](#evaluate-word-error-rate-wer) compared to speech recognition results.
 
+After you [upload training and testing datasets](how-to-custom-speech-upload-data.md), you can create a test.
+
 ::: zone pivot="ai-foundry-portal"
 
+To test your fine-tuned custom speech model, follow these steps:
+
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After the model is trained, select **Test models** from the left menu. Then select **+ Create test**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Test models** > **+ Create test**. 
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-test-model.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png":::
 
 1. In the **Create a new test** wizard, select the test type. For an accuracy (quantitative) test, select **Evaluate accuracy (Audio + transcript data)**. Then select **Next**.
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-test-model-select-type.png" alt-text="Screenshot of the page with an option to select the test type." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-test-model-select-type.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model-select-type.png" alt-text="Screenshot of the page with an option to select the test type." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model-select-type.png":::
 
 1. Select the data that you want to use for testing. Then select **Next**.
 1. Select up to two models to evaluate and compare accuracy. In this example, we select the model that we trained and the base model. Then select **Next**.
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-test-model-select-models.png" alt-text="Screenshot of the page with an option to select up to two models to evaluate and compare accuracy." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-test-model-select-models.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model-select-models.png" alt-text="Screenshot of the page with an option to select up to two models to evaluate and compare accuracy." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model-select-models.png":::
 
 1. Enter a name and description for the test. Then select **Next**.
 1. Review the settings and select **Create test**. You're taken back to the **Test models** page. The status of the data is **Processing**.
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-test-model-status-processing.png" alt-text="Screenshot of the page that shows the status of the test as processing." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-test-model-status-processing.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model-status-processing.png" alt-text="Screenshot of the page that shows the status of the test as processing." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model-status-processing.png":::
 
 ::: zone-end
 

articles/ai-services/speech-service/how-to-custom-speech-human-labeled-transcriptions.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 #Customer intent: As a developer, I need to understand how to create human-labeled transcriptions for my audio data so that I can improve speech recognition accuracy.
 ---

articles/ai-services/speech-service/how-to-custom-speech-inspect-data.md

@@ -6,7 +6,7 @@ author: eric-urban
 manager: nitinme
 ms.service: azure-ai-speech
 ms.topic: how-to
-ms.date: 2/25/2025
+ms.date: 5/19/2025
 ms.author: eur
 zone_pivot_groups: foundry-speech-studio-cli-rest
 #Customer intent: As a developer, I want to test the recognition quality of a custom speech model so that I can determine if the provided recognition result is correct.
@@ -22,21 +22,24 @@ Side-by-side model testing is useful to validate which speech recognition model
 
 ## Create a test
 
+After you [upload training and testing datasets](how-to-custom-speech-upload-data.md), you can create a test.
+
 ::: zone pivot="ai-foundry-portal"
 
+To test your fine-tuned custom speech model, follow these steps:
+
 1. Sign in to the [Azure AI Foundry portal](https://ai.azure.com).
-1. Select **Fine-tuning** from the left pane.
-1. Select **AI Service fine-tuning**.
-1. Select the custom model that you want to manage from the **Model name** column.
-1. After the model is trained, select **Test models** from the left menu. Then select **+ Create test**.
+1. Select **Fine-tuning** from the left pane and then select **AI Service fine-tuning**.
+1. Select the custom speech fine-tuning task (by model name) that you [started as described in the how to start custom speech fine-tuning article](./how-to-custom-speech-create-project.md).
+1. Select **Test models** > **+ Create test**. 
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-test-model.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png" alt-text="Screenshot of the page with an option to test your custom speech model." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model.png":::
 
 1. In the **Create a new test** wizard, select the test type. For a quality test, select **Inspect quality (Audio-only data)**. Then select **Next**.
 1. Select the data that you want to use for testing. Then select **Next**.
 1. Select up to two models to evaluate and compare accuracy. In this example, we select the model that we trained and the base model. Then select **Next**.
 
-    :::image type="content" source="./media/ai-foundry/custom-speech/new-fine-tune-test-model-select-models.png" alt-text="Screenshot of the page with an option to select up to two models to evaluate and compare accuracy." lightbox="./media/ai-foundry/custom-speech/new-fine-tune-test-model-select-models.png":::
+    :::image type="content" source="./media/custom-speech/ai-foundry/new-fine-tune-test-model-select-models.png" alt-text="Screenshot of the page with an option to select up to two models to evaluate and compare accuracy." lightbox="./media/custom-speech/ai-foundry/new-fine-tune-test-model-select-models.png":::
 
 1. Enter a name and description for the test. Then select **Next**.
 1. Review the settings and select **Create test**. You're taken back to the **Test models** page. The status of the data is **Processing**.