> ## Documentation Index
> Fetch the complete documentation index at: https://docs.muna.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Compiling Huggingface Models
> Compile models from Huggingface with zero code.
Muna is the easiest way to run arbitrary models from Huggingface.
## Using our Compiler Agent in Slack
Simply [join our Slack](https://muna.ai) and ask Cursor to compile a model, providing a link to the Huggingface repo:
Our compiler agent is powered by [Agent Skills](https://github.com/muna-ai/agent-skills) that provide detailed instructions on how to write and compile Huggingface models.
The agent will spend anywhere from a few minutes to a few hours writing the required Python inference code for the model, compiling it, and testing that it works:
## Running the Compiled Function
Once compiled, you can run the compiled model anywhere:
```ts JavaScript icon="js" theme={null}
import { Muna } from "muna"
// 💥 Create your Muna client
const openai = new Muna({ accessKey: "..." }).beta.openai;
// 🔥 Make a prediction
const transcription = await openai.audio.transcriptions.create({
model: "moonshine/moonshine-base",
file: audioFile
});
// 🚀 Use the results
console.log(transcription.text);
```
```py Python icon="python" theme={null}
from muna import Muna
# 💥 Create your Muna client
openai = Muna(access_key="...").beta.openai
# 🔥 Make a prediction
transcription = muna.predictions.create(
model="moonshine/moonshine-base",
file=audio_file
)
# 🚀 Use the results
print(transcription.text)
```
## Try it Yourself
Compile a Huggingface model in our community Slack.
Check out some models that have been compiled by our agent.