README.md

---
title: Busy Module Audio Features
emoji: 🎤
colorFrom: indigo
colorTo: purple
sdk: docker
app_port: 7860
pinned: false
---

# Busy Module Audio Features

## Audio Feature Extraction API

Extracts 17 voice features from audio: SNR, noise classification, speech rate, pitch, energy, pause analysis, and emotion features.

## API

**POST** `/extract-audio-features-base64`
```json
{
  "audio_base64": "<base64-encoded-wav>",
  "transcript": "I'm driving right now"
}
```

**POST** `/extract-audio-features` (multipart form)
- `audio`: audio file upload
- `transcript`: text transcript

**POST** `/extract-audio-features` (multipart form)
- `audio`: audio file upload
- `transcript`: text transcript

**GET** `/health`

## Authentication

This Space requires access to private models. You must add your Hugging Face token as a secret:
1. Go to **Settings** -> **Variables and secrets**.
2. Click **New secret**.
3. Name: `HF_TOKEN`
4. Value: Your Hugging Face Access Token (with read permissions).