voice live with agents quickstart

Author: eric-urban

articles/ai-foundry/toc.yml

@@ -483,8 +483,10 @@ items:
     items:
     - name: What is the Speech service?
       href: ../ai-services/speech-service/overview.md?context=/azure/ai-foundry/context/context
-    - name: Voice live
+    - name: Voice live with Foundry models quickstart
       href: ../ai-services/speech-service/voice-live-quickstart.md?context=/azure/ai-foundry/context/context
+    - name: Voice live with Foundry agents quickstart
+      href: ../ai-services/speech-service/voice-live-agents-quickstart.md?context=/azure/ai-foundry/context/context
     - name: Real-time speech to text
       href: ../ai-services/speech-service/get-started-speech-to-text.md?context=/azure/ai-foundry/context/context
     - name: Fast transcription

articles/ai-services/speech-service/includes/quickstarts/voice-live-agents/ai-foundry.md

@@ -33,10 +33,6 @@ To try out the voice live demo, follow these steps:
 
    :::image type="content" source="../../../media/voice-live/foundry-portal/capabilities-by-scenario.png" alt-text="Screenshot of filtering Speech service capabilities by scenario." lightbox="../../../media/voice-live/foundry-portal/capabilities-by-scenario.png":::
 
-1. Select a sample scenario, such as **Casual chat**.
-
-   :::image type="content" source="../../../media/voice-live/foundry-portal/casual-chat-start.png" alt-text="Screenshot of selecting the casual chat example scenario in the Speech playground." lightbox="../../../media/voice-live/foundry-portal/casual-chat-start.png":::
-
 1. Select an agent that you configured in the **Agents** playground.
 
    :::image type="content" source="../../../media/voice-live/foundry-portal/casual-chat-bring-agent-select.png" alt-text="Screenshot of the option to bring an agent for voice live in the speech playground." lightbox="../../../media/voice-live/foundry-portal/casual-chat-bring-agent-select.png":::

articles/ai-services/speech-service/includes/quickstarts/voice-live-agents/python.md

@@ -7,14 +7,14 @@ ms.topic: include
 ms.date: 7/31/2025
 ---
 
-In this article, you learn how to use voice live with [Azure AI Foundry Agent Service](/azure/ai-foundry/agents/overview) and [Azure AI Speech](/azure/ai-services/speech-service/overview) using Python code. 
+In this article, you learn how to use Azure AI Speech voice live with [Azure AI Foundry Agent Service](/azure/ai-foundry/agents/overview) using Python code. 
 
 [!INCLUDE [Introduction](intro.md)]
 
 ## Prerequisites
 
 - An Azure subscription. <a href="https://azure.microsoft.com/free/ai-services" target="_blank">Create one for free</a>.
-- <a href="https://www.python.org/" target="_blank">Python 3.8 or later version</a>. We recommend using Python 3.10 or later, but having at least Python 3.8 is required. If you don't have a suitable version of Python installed, you can follow the instructions in the [VS Code Python Tutorial](https://code.visualstudio.com/docs/python/python-tutorial#_install-a-python-interpreter) for the easiest way of installing Python on your operating system.
+- <a href="https://www.python.org/" target="_blank">Python 3.10 or later version</a>. If you don't have a suitable version of Python installed, you can follow the instructions in the [VS Code Python Tutorial](https://code.visualstudio.com/docs/python/python-tutorial#_install-a-python-interpreter) for the easiest way of installing Python on your operating system.
 - An [Azure AI Foundry resource](../../../../multi-service-resource.md) created in one of the supported regions. For more information about region availability, see the [voice live overview documentation](../../../voice-live.md).
 - An Azure AI Foundry agent created in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs). For more information about creating an agent, see the [Create an agent quickstart](/azure/ai-foundry/agents/quickstart).
 
@@ -103,6 +103,31 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 
 ## Start a conversation
 
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can set the `api_key` variable instead of the `token` variable.
+
+#### [Microsoft Entra ID](#tab/keyless)
+
+```python
+client = AsyncAzureVoiceLive(
+    azure_endpoint = endpoint,
+    api_version = api_version,
+    token = token.token,
+    #api_key = api_key,
+)
+```
+
+#### [API key](#tab/api-key)
+
+```python
+client = AsyncAzureVoiceLive(
+    azure_endpoint = endpoint,
+    api_version = api_version,
+    #token = token.token,
+    api_key = api_key,
+)
+```
+---
+
 1. Create the `voice-live-agents-quickstart.py` file with the following code:
 
     ```python

articles/ai-services/speech-service/includes/quickstarts/voice-live-api/python.md

@@ -7,14 +7,14 @@ ms.topic: include
 ms.date: 7/31/2025
 ---
 
-In this article, you learn how to use voice live with generative AI and Azure AI Speech using Python code. 
+In this article, you learn how to use Azure AI Speech voice live with [Azure AI Foundry models](/azure/ai-foundry/concepts/foundry-models-overview) using Python code.
 
 [!INCLUDE [Introduction](intro.md)]
 
 ## Prerequisites
 
 - An Azure subscription. <a href="https://azure.microsoft.com/free/ai-services" target="_blank">Create one for free</a>.
-- <a href="https://www.python.org/" target="_blank">Python 3.8 or later version</a>. We recommend using Python 3.10 or later, but having at least Python 3.8 is required. If you don't have a suitable version of Python installed, you can follow the instructions in the [VS Code Python Tutorial](https://code.visualstudio.com/docs/python/python-tutorial#_install-a-python-interpreter) for the easiest way of installing Python on your operating system.
+- <a href="https://www.python.org/" target="_blank">Python 3.10 or later version</a>. If you don't have a suitable version of Python installed, you can follow the instructions in the [VS Code Python Tutorial](https://code.visualstudio.com/docs/python/python-tutorial#_install-a-python-interpreter) for the easiest way of installing Python on your operating system.
 - An [Azure AI Foundry resource](../../../../multi-service-resource.md) created in one of the supported regions. For more information about region availability, see the [voice live overview documentation](../../../voice-live.md).
 
 > [!TIP]
@@ -102,6 +102,31 @@ For the recommended keyless authentication with Microsoft Entra ID, you need to:
 
 ## Start a conversation
 
+The sample code in this quickstart uses Microsoft Entra ID for the recommended keyless authentication. If you prefer to use an API key, you can set the `api_key` variable instead of the `token` variable.
+
+#### [Microsoft Entra ID](#tab/keyless)
+
+```python
+client = AsyncAzureVoiceLive(
+    azure_endpoint = endpoint,
+    api_version = api_version,
+    token = token.token,
+    #api_key = api_key,
+)
+```
+
+#### [API key](#tab/api-key)
+
+```python
+client = AsyncAzureVoiceLive(
+    azure_endpoint = endpoint,
+    api_version = api_version,
+    #token = token.token,
+    api_key = api_key,
+)
+```
+---
+
 1. Create the `voice-live-quickstart.py` file with the following code:
 
     ```python

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

@@ -238,7 +238,7 @@ items:
   items:
     - name: Voice live overview
       href: voice-live.md
-    - name: Voice live quickstart
+    - name: Voice live with Foundry models quickstart
       href: voice-live-quickstart.md
     - name: Voice live with Foundry agents quickstart
       href: voice-live-agents-quickstart.md