📋 SRS Generator

An intelligent tool that converts video meetings and discussions into comprehensive Software Requirements Specification (SRS) documents using AI-powered transcription and analysis.

🚀 Features

• 🎥 Video Processing: Extract audio from various video formats (MP4, AVI, MOV, MKV)
• 🌍 Multilingual Support: Automatic language detection and transcription using OpenAI Whisper
• 🤖 AI-Powered Analysis: Convert transcripts to structured SRS documents using Ollama (local AI models)
• 📱 Web Interface: Beautiful Streamlit web application for easy use
• 💻 Command Line: CLI interface for automation and scripting
• 📄 Multiple Outputs: Generate both SRS documents and transcripts
• 🎨 Modern UI: Clean, responsive web interface with real-time progress tracking

📋 What is SRS?

A Software Requirements Specification (SRS) is a document that describes what the software will do and how it will be expected to perform. It serves as a contract between the development team and stakeholders, ensuring everyone understands the project requirements.

🛠️ Installation

Prerequisites

• Python 3.8 or higher
• FFmpeg (for video processing)
• Ollama (for local AI models)

Install FFmpeg

Windows:

# Using Chocolatey
choco install ffmpeg

# Or download from https://ffmpeg.org/download.html

macOS:

# Using Homebrew
brew install ffmpeg

Linux (Ubuntu/Debian):

sudo apt update
sudo apt install ffmpeg

Install Python Dependencies

1. Clone the repository:

git clone <repository-url>
cd srs-generator

2. Install Python dependencies:

pip install -r requirements.txt

3. Install and set up Ollama:

# Run the setup script
python setup_ollama.py

# Or manually install Ollama from https://ollama.ai/download
# Then pull a model:
ollama pull llama3.2

🔑 Ollama Setup

Installing Ollama

1. Download Ollama from https://ollama.ai/download
2. Install and start the Ollama service
3. Pull a model: ollama pull llama3.2

Available Models

The application supports various Ollama models:

• llama3.2 (recommended)
• llama3.1
• llama2
• mistral
• codellama
• phi3

Choose the model based on your hardware capabilities and quality requirements.

🚀 Usage

Web Interface (Recommended)

Launch the Streamlit web application:

streamlit run app.py

Then open your browser to http://localhost:8501

Command Line Interface

Basic Usage

# Generate SRS from video file
python cli.py video.mp4 --project "My Project"

# Generate SRS with custom output file
python cli.py meeting.avi --output my_srs.md

# Only generate transcript (skip SRS generation)
python cli.py audio.wav --transcript-only

Advanced Options

# Use specific API key
python cli.py video.mp4 --api-key YOUR_API_KEY

# Verbose output
python cli.py video.mp4 --verbose

# Use different Whisper model
python cli.py video.mp4 --whisper-model large

CLI Help

python cli.py --help

Programmatic Usage

from srs_generator import SRSGenerator

# Initialize the generator
generator = SRSGenerator(gemini_api_key="your_api_key")

# Process video to SRS
result = generator.process_video_to_srs("video.mp4", "My Project")

# Access results
print(result["transcript"]["text"])  # Raw transcript
print(result["srs_document"])        # Generated SRS

📁 Supported Formats

Video Formats

• MP4
• AVI
• MOV
• MKV
• And more (via FFmpeg)

Audio Formats

• MP3
• WAV
• M4A
• And more (via FFmpeg)

Languages

• All major languages supported by OpenAI Whisper
• Automatic language detection
• Multilingual content handling

📄 Output Structure

The generated SRS document follows the IEEE 830 standard and includes:

1. Introduction

   • Purpose
   • Scope
   • Definitions, Acronyms, and Abbreviations
   • References
   • Overview

2. Overall Description

   • Product Perspective
   • Product Functions
   • User Classes and Characteristics
   • Operating Environment
   • Design and Implementation Constraints
   • User Documentation
   • Assumptions and Dependencies

3. Specific Requirements

   • Functional Requirements
   • External Interface Requirements
   • Performance Requirements
   • Design Constraints
   • Software System Attributes

4. Appendices

   • Glossary
   • Analysis Models

🔧 Configuration

Environment Variables

Create a .env file in the project root:

GEMINI_API_KEY=your_gemini_api_key_here
OPENAI_API_KEY=your_openai_api_key_here  # Optional

Whisper Models

Choose from different Whisper model sizes:

• tiny: Fastest, least accurate
• base: Good balance (default)
• small: Better accuracy
• medium: High accuracy
• large: Best accuracy, slowest

🐛 Troubleshooting

Common Issues

1. FFmpeg not found

   • Install FFmpeg and ensure it's in your PATH
   • Restart your terminal after installation

2. API key errors

   • Verify your Gemini API key is correct
   • Check that the API key has proper permissions

3. Memory issues with large videos

   • Use a smaller Whisper model
   • Consider processing shorter video segments

4. Slow processing

   • Use a smaller Whisper model
   • Ensure you have sufficient RAM
   • Consider using GPU acceleration if available

Getting Help

If you encounter issues:

1. Check the error messages in the console
2. Verify all dependencies are installed
3. Ensure API keys are properly configured
4. Check that input files are valid and accessible

🤝 Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

🙏 Acknowledgments

• OpenAI Whisper for speech recognition
• Google Gemini for AI-powered analysis
• Streamlit for the web interface
• MoviePy for video processing

📞 Support

For support and questions:

• Open an issue on GitHub
• Check the troubleshooting section
• Review the documentation

---

Happy SRS Generation! 📋✨