---
title: "Fermion runtime documentation"
description: "Install fermion, run Neutrino and Phonon models locally, chat, transcribe and dictate, serve an OpenAI-compatible API, and call tools."
canonical: "https://www.fermionresearch.com/docs/"
source: "Fermion Research"
---

Documentation / Overview

# Fermion runtime documentation

Run Neutrino and Phonon models locally: chat, transcribe and dictate, expose an OpenAI-compatible API, and call tools.

Quickstart

## Start a local chat

Python 3.10 or newer. The first run downloads and verifies the model.

```text
pip install fermion-research
fermion chat
```

Speech

## Transcribe and dictate

Same install. The first run downloads and verifies Phonon-1.

```text
fermion transcribe recording.wav
fermion listen
```

## Start building

Choose the path closest to what you are trying to do.

## Guides and reference

Source: [https://www.fermionresearch.com/docs/](https://www.fermionresearch.com/docs/)