You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: articles/ai-services/speech-service/includes/quickstarts/voice-live-agents/ai-foundry.md
+3-1Lines changed: 3 additions & 1 deletion
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -9,7 +9,9 @@ ms.date: 7/31/2025
9
9
ms.custom: references_regions
10
10
---
11
11
12
-
In this article, you learn how to use voice live with generative AI and Azure AI Speech in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs).
12
+
In this article, you learn how to use voice live with agents and Azure AI Speech in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs).
You can create and run an application to use voice live with agents for real-time voice agents.
10
+
11
+
- Using agents allows leveraging a built-in prompt and configuration managed within the agent itself, rather than specifying instructions in the session code.
12
+
13
+
- Agents encapsulate more complex logic and behaviors, making it easier to manage and update conversational flows without changing the client code.
14
+
15
+
- The agent approach streamlines integration. The agent ID is used to connect and all necessary settings are handled internally, reducing the need for manual configuration in the code.
16
+
17
+
- This separation also supports better maintainability and scalability for scenarios where multiple conversational experiences or business logic variations are needed.
18
+
19
+
To instead use the voice live API without agents, see the [voice live quickstart](/azure/ai-services/speech-service/voice-live-quickstart).
Copy file name to clipboardExpand all lines: articles/ai-services/speech-service/includes/quickstarts/voice-live-api/ai-foundry.md
+2Lines changed: 2 additions & 0 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -11,6 +11,8 @@ ms.custom: references_regions
11
11
12
12
In this article, you learn how to use voice live with generative AI and Azure AI Speech in the [Azure AI Foundry portal](https://ai.azure.com/?cid=learnDocs).
13
13
14
+
[!INCLUDE [Introduction](intro.md)]
15
+
14
16
## Prerequisites
15
17
16
18
- An Azure subscription. <ahref="https://azure.microsoft.com/free/ai-services"target="_blank">Create one for free</a>.
You create and run an application to use voice live directly with generative AI models for real-time voice agents.
10
+
11
+
- Using models directly allows specifying custom instructions (prompts) for each session, offering more flexibility for dynamic or experimental use cases.
12
+
13
+
- Models may be preferable when you want fine-grained control over session parameters or need to frequently adjust the prompt or configuration without updating an agent in the portal.
14
+
15
+
- The code for model-based sessions is simpler in some respects, as it does not require managing agent IDs or agent-specific setup.
16
+
17
+
- Direct model use is suitable for scenarios where agent-level abstraction or built-in logic is unnecessary.
18
+
19
+
To instead use the voice live API with agents, see the [voice live agents quickstart](/azure/ai-services/speech-service/voice-live-agents-quickstart).
0 commit comments