Agents-MCP-Hackathon/VTS

🎙️ Professional Audio/Video AI Suite

Hackathon Track: Agent-Demo-Track Gradio Agents & MCP Hackathon 2025

🌟 Overview

The Professional Audio/Video AI Suite is an advanced AI-powered application that transforms audio and video content through intelligent processing. This comprehensive tool demonstrates the power of AI agents by seamlessly integrating multiple AI models, speech recognition, and text-to-speech capabilities to provide 10+ specialized content processing services.


🔔 Note – Only English audio/video is supported. Videos must be under 60 seconds.

🎯 Key Features

🤖 Multi-Agent AI Processing

• —Dual AI Model Support: Google Gemini 1.5 Flash & DeepSeek R1
• —Intelligent Service Selection: 10 specialized AI agents for different content types
• —Context-Aware Processing: Each agent optimized for specific use cases

🌍 Multilingual Capabilities

• —11 Language Support: Hindi, Nepali, Spanish, French, German, Chinese, Japanese, Korean, Arabic, Russian, Portuguese
• —Real-time Translation: Instant translation with audio output generation
• —Cross-language Summaries: AI-powered multilingual content summaries

📊 Professional Content Processing

• —Structured Output Formatting: Service-specific professional layouts
• —Multiple Content Types: Audio (.wav, .mp3, .ogg, .webm, .flac) and Video (.mp4, .mov, .avi, .mkv)
• —Intelligent Transcription: Advanced speech recognition with noise filtering

🛠️ Available AI Services

🚀 Technical Architecture

AI Agent Framework

User Input → Speech Recognition → AI Agent Selection → Content Processing → Professional Formatting → Output Generation

Core Technologies

• —Frontend: Gradio 4.44.0 with custom CSS styling
• —Speech Processing: Google Speech Recognition API
• —AI Models:
• —Google Gemini 1.5 Flash (Fast processing)
• —DeepSeek R1 (Detailed analysis)
• —Text-to-Speech: Google Text-to-Speech (gTTS)
• —Media Processing: FFmpeg for video-to-audio conversion

Smart Features

• —Adaptive Language Detection: Automatic service-based language dropdown
• —Professional Text Formatting: Service-specific output structures
• —Error Handling: Comprehensive validation and user feedback
• —File Management: Temporary file cleanup and optimization

📱 User Experience

Intuitive Interface

• —Drag & Drop Upload: Easy file selection
• —Smart Service Selection: Context-aware options
• —Real-time Processing: Live status updates
• —Professional Results: Clean, formatted output

Accessibility Features

• —Responsive Design: Works on all devices
• —Clear Visual Hierarchy: Professional styling
• —Copy Functionality: Easy content sharing
• —Audio Playback: Generated audio for translations

🎥 Demo Video

**Watch Demo Video**

The demo showcases:

• —File upload and processing workflow
• —Multiple AI service demonstrations
• —Multilingual translation with audio output
• —Professional formatting examples
• —Real-time processing capabilities

🏆 Hackathon Relevance

Agent-Demo-Track Alignment

This application perfectly demonstrates the power of AI agents through:

1. 1.Multi-Agent Architecture: 10 specialized AI agents for different content types
2. 2.Intelligent Routing: Smart service selection based on user needs
3. 3.Context Awareness: Each agent optimized for specific use cases
4. 4.Professional Output: Service-specific formatting and structure
5. 5.Real-world Applications: Practical solutions for content creators, educators, and professionals

Innovation Highlights

• —Seamless Integration: Multiple AI models working together
• —Professional Formatting: Service-specific output structures
• —Multilingual Support: 11 languages with audio generation
• —User-Centric Design: Intuitive interface with professional results

🚀 Getting Started

Prerequisites

pip install gradio google-generativeai openai speech-recognition gtts python-dotenv