> For the complete documentation index, see [llms.txt](https://docs.voipnumber.net/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.voipnumber.net/how-to/whispering-ai-agent.md).

# Whispering AI Agent

## What can I do with media routing?

A cool example application of our [Media routing](/features/media-routing.md) feature is a *whispering* AI Agent

When Alice calls Bob, Alice my be running an AI Agent which processes Bob's voice, but whose output (in the form of agent's voice) can be heard by Alice only

Let's set this up

{% embed url="<https://youtu.be/EtVWX8ZqGI4>" %}

## Setup

1. Create outbound [Call Flow](/components/call-flow.md) and add AI Agent action
2. On the AGENT tab select from your agents
3. Go to MEDIA tab and configure input and output to `From VoIP Number` . This will run agent on a media sent from called party and to play agent's voice on the same channel (to yourself)&#x20;

💡 You could also create inbound flow instead

<figure><img src="/files/eeqppbCmX9YRSUKrClHL" alt=""><figcaption></figcaption></figure>

💡 This can be done in an opposite direction too of course, or in both directions at the same time, and you may even think of making same agent's voice available to both Alice and Bob

✅ You now have created [AI Agent](/components/ai-agent.md) that hears what's spoken by the one you called but whispers only to yourself


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.voipnumber.net/how-to/whispering-ai-agent.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.