> ## Documentation Index
> Fetch the complete documentation index at: https://hanabiaiinc-codex-pronunciation-dictionary-instructions.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# Local Model Setup

> Install and configure Fish Audio models for local inference

<Note>
  This guide is for advanced users who want to self-host Fish Audio models. For most users, we recommend using the [Fish Audio API](https://fish.audio) for easier integration and automatic updates.
</Note>

## Prerequisites

Before you begin, ensure you have:

* **GPU**: 12GB VRAM minimum (for inference)
* **OS**: Linux or WSL (Windows Subsystem for Linux)
* **System dependencies**: Audio processing libraries

Install required system packages:

```bash theme={null}
apt install portaudio19-dev libsox-dev ffmpeg
```

## Installation Methods

Fish Audio supports multiple installation methods. Choose the one that best fits your development environment.

### Conda Installation

Conda provides a stable, isolated Python environment:

```bash theme={null}
# Create a new environment with Python 3.12
conda create -n fish-speech python=3.12
conda activate fish-speech

# GPU installation (choose your CUDA version: cu126, cu128, cu129)
pip install -e .[cu129]

# CPU-only installation (slower, not recommended for production)
pip install -e .[cpu]

# Default installation (uses PyTorch default index)
pip install -e .
```

<Tip>
  For best performance, match your CUDA version with your GPU driver. Use `nvidia-smi` to check your CUDA version.
</Tip>

### UV Installation

[UV](https://github.com/astral-sh/uv) provides faster dependency resolution and installation:

```bash theme={null}
# GPU installation (choose your CUDA version: cu126, cu128, cu129)
uv sync --python 3.12 --extra cu129

# CPU-only installation
uv sync --python 3.12 --extra cpu
```

<Note>
  UV is recommended for faster setup times, especially when working with large dependency trees.
</Note>

### Intel Arc XPU Support

For Intel Arc GPU users, install with XPU support:

```bash theme={null}
# Create environment
conda create -n fish-speech python=3.12
conda activate fish-speech

# Install required C++ standard library
conda install libstdcxx -c conda-forge

# Install PyTorch with Intel XPU support
pip install --pre torch torchvision torchaudio --index-url https://download.pytorch.org/whl/nightly/xpu

# Install Fish Speech
pip install -e .
```

<Warning>
  The `--compile` optimization flag is not supported on Windows and macOS. To use compile acceleration, you need to install Triton manually.
</Warning>

## Repository Setup

Clone the Fish Speech repository to get started:

```bash theme={null}
git clone https://github.com/fishaudio/fish-speech.git
cd fish-speech
```

Then follow one of the installation methods above.

## Next Steps

Once installation is complete, you can:

* **[Set up Docker deployment](/developer-guide/self-hosting/docker-deployment)** - Use containerized deployment for easier management
* **[Run inference](/developer-guide/self-hosting/running-inference)** - Start generating speech with your local models
* **Download models** - Get pre-trained weights from [Hugging Face](https://huggingface.co/fishaudio)

## Hardware Recommendations

For optimal performance:

| Use Case    | Recommended GPU | VRAM  | Expected Speed          |
| ----------- | --------------- | ----- | ----------------------- |
| Development | RTX 3060        | 12GB  | \~1:15 real-time factor |
| Production  | RTX 4090        | 24GB  | \~1:7 real-time factor  |
| Enterprise  | A100            | 40GB+ | \~1:5 real-time factor  |

<Info>
  Real-time factor indicates how much faster than real-time the model can generate audio. For example, 1:7 means generating 1 minute of audio takes \~8.5 seconds.
</Info>

## Troubleshooting

### CUDA Out of Memory

If you encounter CUDA out of memory errors:

1. Reduce batch size in inference settings
2. Use `--half` flag for FP16 inference
3. Close other GPU-intensive applications

### Package Installation Errors

If you encounter dependency conflicts:

1. Try using UV instead of pip for better dependency resolution
2. Create a fresh conda environment
3. Ensure you're using Python 3.12 (other versions may have compatibility issues)

## Community Support

Need help with local setup?

* Join our [Discord community](https://discord.gg/dF9Db2Tt3Y) for community support
* Check [GitHub Issues](https://github.com/fishaudio/fish-speech/issues) for known problems
* Contact [enterprise support](mailto:support@fish.audio) for commercial deployments