> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gidr.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Voice ReAct Node

> A specialized ReAct agent optimized for real-time voice interactions.

The **Voice ReAct Node** extends the capabilities of the standard ReAct node by adding real-time speech processing. It is designed to function as a conversational agent that can listen, think, act, and speak back to the user.

## Typical Usage

This node is the centerpiece of voice-enabled workflows, often used for customer service bots, interactive assistants, or accessibility tools.

### Example Configuration

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/voice-react-clean-workflow.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=bf2e51da83cb04e20a441392ed12ce8d" alt="Voice ReAct Node Clean Workflow" width="2770" height="1844" data-path="images/ai-studio/voice-react-clean-workflow.png" />

1. **Connection**: Connected linearly between a Start and End node.
2. **Voice Interaction**: The node handles the complexity of speech-to-text (STT) and text-to-speech (TTS) automatically.

## Configuration Details

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/voice-react-config-top.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=473b14b4f742114b06c7ec77e103f252" alt="Voice ReAct Config Top Section" style={{ width: '300px' }} width="644" height="856" data-path="images/ai-studio/voice-react-config-top.png" />

### Core Settings

* **Title**: Give your voice agent a persona-based name (e.g., "Support Voice Bot").
* **Description**: Internal notes on the agent's role.
* **Agent Language**: The primary language the agent will understand and speak (e.g., "English").

***

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/voice-react-config-middle.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=145caec6ce374438ef743169a1250c77" alt="Voice ReAct Config Middle Section" style={{ width: '300px' }} width="644" height="856" data-path="images/ai-studio/voice-react-config-middle.png" />

### Voice & Personality

* **Additional Languages**: Select other languages the agent should be able to process if supporting a multilingual user base.
* **Voices**: Choose the specific voice model (e.g., "Gemini - Mark (US English Male)") that best fits your brand or use case.
* **First Message**: The opening line the agent will speak when the session starts (e.g., "Hello, I am GIDR Voice Agent. How may I help you today?").

***

<img src="https://mintcdn.com/gidrai/La57oM6sCecLAz60/images/ai-studio/voice-react-config-bottom.png?fit=max&auto=format&n=La57oM6sCecLAz60&q=85&s=7123194cd54469c4c602735a95b1be27" alt="Voice ReAct Config Bottom Section" style={{ width: '300px' }} width="644" height="856" data-path="images/ai-studio/voice-react-config-bottom.png" />

### Prompts & Tools

* **Prompt**: The system instruction defining the agent's behavior, knowledge boundaries, and personality traits.
* **LLM**: The underlying model powering the conversation (e.g., Gemini 2.5 Flash Lite).
* **Tools**: Enable specific tools this voice agent can call while talking to the user.
* **Custom MCP Server**: Extend the agent's capabilities with custom Model Context Protocol servers.