> 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.

# NeMo Voice Agent

NeMo Voice Agent is an open source Python framework for building and evaluating real-time voice agents. It
combines streaming automatic speech recognition (ASR), turn taking, large language model (LLM) inference, and
text-to-speech (TTS) services in a Pipecat pipeline. The repository also provides a browser client and a
spoken-conversation evaluation harness.

## Skip Ahead

Use the following paths to find the information that matches your goal.

| I Want to | Start Here |
| --- | --- |
| Understand the system | [Architecture](/nemo/labs-voice-agent/about/architecture) |
| Run the default voice agent | [Choose your path](/nemo/labs-voice-agent/get-started/choose-your-path) |
| Configure or extend an agent | [Build Voice Agents](/nemo/labs-voice-agent/build-voice-agents/overview) |
| Measure an agent | [Evaluate Voice Agents](/nemo/labs-voice-agent/evaluate-voice-agents/overview) |
| Resolve a problem | [Troubleshooting](/nemo/labs-voice-agent/troubleshooting/troubleshooting) |

## Use Cases

NeMo Voice Agent supports the following voice-agent development and evaluation use cases.

- Run a local voice pipeline with configurable speech, language, and text-to-speech models.
- Connect supported stages to hosted NVIDIA endpoints.
- Add application tools or custom frame processors.
- Evaluate an in-repository or external voice agent through live audio conversations.

## Core Concepts

Start with these explanations to understand how the framework processes speech and generates responses.

- [Speech pipeline](/nemo/labs-voice-agent/about/core-concepts/speech-pipeline/overview) covers recognition, diarization, turn taking,
  and synthesis.
- [Language models](/nemo/labs-voice-agent/about/core-concepts/language-models/overview) covers backends, reasoning, and multimodal
  execution.
- [Architecture](/nemo/labs-voice-agent/about/architecture) shows how the pipeline stages and control messages fit together.

## Core Components

The following components work together to provide the runtime and evaluation experiences.

| Component | Role |
| --- | --- |
| Browser client | Captures microphone audio, opens the WebSocket session, and plays assistant audio. |
| Voice-agent server | Loads configuration, builds the Pipecat pipeline, and serves one client connection. |
| Model services | Provide ASR, LLM, diarization, turn-taking, and TTS behavior. |
| Evaluation harness | Connects a simulated user and agent, records artifacts, and scores scenario outcomes. |

For dated project updates, refer to [Release Notes](/nemo/labs-voice-agent/about/release-notes).