> For the complete documentation index, see [llms.txt](https://helpdocumentation.gitbook.io/user/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://helpdocumentation.gitbook.io/user/voice-ai/voice-ai-overview-in-english.md).

# Voice AI Overview In English

* **Voice AI** is an enterprise-ready platform that lets you build AI voice agents that can **listen, understand, and speak** to customers in real time.
* A **Voice Agent** is an AI assistant that talks naturally with users, understands voice input, and replies with human-like speech.
* From the **Voice Agent Dashboard**, you can view all agents, check widget IDs, AI models used, and track creation or update history.
* To create a new agent, click **Create New Agent**, add the **agent name**, and write instructions defining personality, tone, behavior, and role (e.g., support agent or sales assistant).
* Set a **welcome message** (first sentence spoken during calls).
* Configure **silence timeout** and **off-topic question limit** to control call behavior.
* The Voice AI pipeline includes:
  * **STT (Speech-to-Text)** – converts voice into text
  * **LLM** – understands intent and generates responses
  * **TTS (Text-to-Speech)** – converts replies into natural voice
* Choose the **AI model, voice type, language**, and enable **noise cancellation** for clearer conversations.
* Customize **appearance and branding** by adding logo, colors, button text, widget position, and UI style.
* Preview the widget live, then **save the agent** and copy the **widget code** to embed on your website.
* Once deployed, the voice agent can handle **customer support, lead qualification, booking assistance, product explanations, or AI receptionist tasks** — available **24/7**.

{% embed url="<https://youtu.be/BjnB_CH27WY>" %}


---

# 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 by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://helpdocumentation.gitbook.io/user/voice-ai/voice-ai-overview-in-english.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.