> 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.

# Language Models

The large language model (LLM) stage receives the aggregated conversation context and streams the assistant
response to text-to-speech. NeMo Voice Agent can run a Hugging Face model in the server process, call a vLLM
server, or use a hosted NVIDIA endpoint.

## Core Concepts

The following pages explain how language models generate, reason about, and consume voice-agent context.

| Concept | What It Explains |
| --- | --- |
| [LLM backends](/nemo/labs-voice-agent/about/core-concepts/language-models/llm-backends) | Backend selection, configuration layers, and supported tool-calling paths. |
| [Reasoning mode](/nemo/labs-voice-agent/about/core-concepts/language-models/reasoning-mode) | Thinking configurations and how reasoning text is kept out of speech. |
| [Multimodal and omni models](/nemo/labs-voice-agent/about/core-concepts/language-models/multimodal-omni) | Direct audio input and the additional user-audio buffer stage. |

Model concepts describe runtime behavior. For deployment and endpoint setup, continue to
[Serving with vLLM](/nemo/labs-voice-agent/build-voice-agents/model-serving/serving-with-v-llm),
[vLLM Plugins](/nemo/labs-voice-agent/build-voice-agents/model-serving/v-llm-plugins), or
[NVIDIA NIM and Riva](/nemo/labs-voice-agent/build-voice-agents/model-serving/nvidia-nim-riva).

## Related Topics

Use these pages to configure model behavior, serve a backend, or connect models to application tools.

- [System prompts](/nemo/labs-voice-agent/build-voice-agents/configure/system-prompts) — control assistant behavior.
- [Tool calling](/nemo/labs-voice-agent/build-voice-agents/tools/tool-calling) — let supported backends call functions.