> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/labs-voice-agent/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/labs-voice-agent/_mcp/server.

# Choose Your Path

Use this page to select the documentation path that matches your goal. Each path assumes a source checkout
of the repository. The installation script creates the project virtual environment.

Before you begin, review [Prerequisites](/nemo/labs-voice-agent/get-started/prerequisites) for the system, software, and audio requirements.

## Choose by Goal

Match your goal to its starting page, then follow the related guide for the next part of the workflow:

| Goal | Start Here | Continue With |
| --- | --- | --- |
| Talk to the default agent | [Prerequisites](/nemo/labs-voice-agent/get-started/prerequisites) | [Installation](/nemo/labs-voice-agent/get-started/installation), then [Quickstart](/nemo/labs-voice-agent/get-started/quickstart) |
| Understand the pipeline first | [Overview](/nemo/labs-voice-agent/about/overview) | [Architecture](/nemo/labs-voice-agent/about/architecture) |
| Change models or behavior | [Configure](/nemo/labs-voice-agent/build-voice-agents/configure/overview) | [Serving with vLLM](/nemo/labs-voice-agent/build-voice-agents/model-serving/serving-with-v-llm) or [Tool Calling](/nemo/labs-voice-agent/build-voice-agents/tools/tool-calling) |
| Add pipeline code | [Extend](/nemo/labs-voice-agent/build-voice-agents/extend/overview) | [Builder API](/nemo/labs-voice-agent/build-voice-agents/extend/pipelines/the-builder-api) or [RTVI Control Plane](/nemo/labs-voice-agent/build-voice-agents/extend/protocols/rtvi-control-plane) |
| Measure an agent | [Evaluation overview](/nemo/labs-voice-agent/evaluate-voice-agents/overview) | [Evaluation Quickstart](/nemo/labs-voice-agent/evaluate-voice-agents/run-evaluations/quickstart) |

## First-Run Sequence

For the shortest path to a working browser session:

1. Verify the [prerequisites](/nemo/labs-voice-agent/get-started/prerequisites).
2. [Install](/nemo/labs-voice-agent/get-started/installation) the Python environment and browser dependencies.
3. Complete the [quickstart](/nemo/labs-voice-agent/get-started/quickstart) to launch vLLM, the agent server, and the client.

If a step fails, use [Troubleshooting](/nemo/labs-voice-agent/troubleshooting/troubleshooting).