🔄 OmniConv

Universal AI-Powered File Converter & Compressor
Convert audio, video, images, and documents with OCR support — all locally, no cloud needed.

Features • Quick Start • Formats • Tech Stack •

---

✨ Features

---

🚀 Quick Start

Prerequisites

• Python
• FFmpeg (for audio/video processing)

Installation

# Clone the repository
git clone https://github.com/PanPeryskop/OmniConv
cd OmniConv

# Create virtual environment
python -m venv .venv

# Activate virtual environment
# Windows:
.venv\Scripts\activate
# Linux/macOS:
source .venv/bin/activate

# Install dependencies
pip install -r requirements.txt

# Run the application
python run.py

🌐 Open in Browser

http://localhost:5000

---

📋 Supported Formats

🎵 Audio Formats

Input	Output
MP3, WAV, OGG, FLAC, M4A, AAC, AC3, ALAC, DTS, EAC3, TTA, WV, AIFF, APE, WMA, OPUS	MP3, WAV, OGG, FLAC, M4A, AIFF

🎬 Video Formats

Input	Output
MP4, AVI, MKV, MOV, WMV, FLV, WEBM, 3GP, MPEG, M4V, TS, MTS, VOB	MP4, WEBM, AVI, MKV, MOV, GIF

💡 Tip: You can also extract audio from videos to MP3, WAV, AAC, or OGG!

🖼️ Image Formats

Input	Output
JPG, JPEG, PNG, GIF, BMP, TIFF, WEBP, ICO, HEIC, HEIF	PNG, JPG, WEBP, GIF, BMP, TIFF, ICO, PDF

📄 Document Formats

Input	Output
PDF, DOCX, DOC, TXT, RTF, ODT, XLS, XLSX, MD	DOCX, PDF, TXT, EPUB, CBZ

🔍 OCR Engine Options:

• Qwen 3-VL: State-of-the-art multimodal AI (high accuracy, slower).
• LightOn (PaddleOCR): Fast, local OCR engine for raw text extraction.
• LightOn + Mistral: Combines fast PaddleOCR extraction with Mistral 3-3B for smart text correction.

---

🛠️ Tech Stack

---

🏠 Main Converter

Clean, intuitive interface for single file conversion with drag & drop support.

📦 Batch Conversion

Process multiple files at once — grouped by type with individual format selection.

🗜️ Smart Compression

Set your target file size and let the AI optimize quality automatically.

📜 Conversion History

Track all your conversions with timestamps and easy re-download.

---

📁 Project Structure

OmniConv/
├── app/
│   ├── routes/
│   │   ├── api.py          # REST API endpoints
│   │   └── views.py        # Page routes
│   ├── services/
│   │   ├── audio.py        # Audio conversion
│   │   ├── video.py        # Video conversion
│   │   ├── image.py        # Image conversion
│   │   ├── document.py     # Document conversion
│   │   ├── compressor.py   # File compression
│   │   └── ocr.py          # OCR service
│   ├── static/
│   │   ├── css/styles.css  # Styling
│   │   └── js/app.js       # Frontend logic
│   └── templates/          # HTML templates
├── uploads/                # Temporary uploads
├── outputs/                # Converted files
├── requirements.txt
└── run.py                  # Entry point

---

⚙️ Configuration

Environment variables (optional):