Data

Tools

Indexes

Applications

Experiments

Open Source Science

real_time_genai_teleprompter

https://github.com/shruti192903/real_time_genai_teleprompter

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (12.9%) to scientific vocabulary
Last synced: 10 months ago · JSON representation ·

Repository

Basic Info
  • Host: GitHub
  • Owner: Shruti192903
  • Language: Python
  • Default Branch: main
  • Size: 287 KB
Statistics
  • Stars: 0
  • Watchers: 0
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 12 months ago · Last pushed 12 months ago
Metadata Files
Readme Citation

README.md

🎤 Real-Time GenAI TelePrompter

Streamlit App Python OpenAI Whisper

AI-Powered Sales Coach with Real-Time Speech Transcription and Intelligent Coaching Suggestions

A cutting-edge AI application that provides real-time speech transcription and intelligent sales coaching suggestions to help sales professionals improve their performance during live conversations.

🌟 Features

🎯 Core Functionality

  • 🎤 Real-Time Speech Transcription: High-accuracy speech-to-text using OpenAI Whisper.
  • 🤖 AI-Powered Coaching: GPT-4o generates contextual sales suggestions.
  • 🌍 Multi-Language Support: Supports multiple languages with auto-detection.
  • 📱 Professional UI: Dark-themed, responsive web interface.
  • 🔄 Real-Time Processing: 5-second audio cycles for immediate feedback.

🚀 Advanced Features

  • Dual AI System: GPT-4o intelligence with rule-based fallback.
  • Conversation Context: AI understands conversation flow.
  • Debug Mode: Comprehensive troubleshooting tools.
  • Session Export: JSON and TXT format downloads.
  • Audio Quality Monitoring: Real-time audio feedback.
  • Visual Status Indicators: Clear recording states.

📸 Main Interface

Main Interface

🛠️ Installation

Prerequisites

  • Python 3.8 or higher
  • Microphone access
  • Internet connection
  • OpenAI API key (optional, for AI features)

Quick Start

  1. Clone the repository git clone https://github.com/Shruti192903/Real_Time_GenAI_TelePrompter.git cd Real_Time_GenAI_TelePrompter
  2. Create virtual environment python -m venv venv source venv/bin/activate # On Windows: venv\Scripts\activate
  3. Install Dependencies pip install -r requirements.txt
  4. Set up OpenAI API Key (Optional)
    • Method 1: Set environment variable export OPENAI_API_KEY="your-api-key-here"
    • Method 2: Streamlit secrets
      • Create a folder named .streamlit in your project root, and inside it, create a file named secrets.toml. # .streamlit/secrets.toml OPENAI_API_KEY = "your-api-key-here"
  5. Run the application streamlit run app.py
  6. Open in browser

🗂️ Project Structure

Real_Time_GenAI_TelePrompter/ │ ├── app.py ├── requirements.txt ├── README.md ├── .gitignore └── .streamlit/ └── secrets.toml

⚙️ Usage

  • Click Start Recording to begin capturing audio in real time (5-second cycles).
  • View live transcripts and AI sales suggestions side-by-side.
  • Switch between AI-powered and rule-based suggestions in the sidebar.
  • Enable Debug Mode for troubleshooting and audio device info.
  • Export your session as JSON or TXT after stopping the recording.

💡 Tips

  • Speak clearly and minimize background noise.
  • Use Debug Mode if you have issues with audio or transcription.
  • For best AI suggestions, provide your OpenAI API key in the sidebar.

## ⭐ Acknowledgements

Owner

  • Login: Shruti192903
  • Kind: user

Citation (CITATIONS.md) 

# Code Citations and Attributions

## Project Overview
This TelePrompter application is an original implementation combining multiple open-source libraries and frameworks to create a real-time AI-powered sales coaching tool.

## Third-Party Libraries and Dependencies

### Core Framework
- **Streamlit** - Web application framework
  - License: Apache 2.0
  - Source: https://github.com/streamlit/streamlit

### Audio Processing
- **OpenAI Whisper** - Speech recognition model
  - License: MIT
  - Source: https://github.com/openai/whisper

- **sounddevice** - Audio recording library
  - License: MIT
  - Source: https://github.com/spatialaudio/python-sounddevice

- **NumPy** - Numerical computing
  - License: BSD-3-Clause
  - Source: https://github.com/numpy/numpy

### AI Integration
- **OpenAI Python Library** - GPT API client
  - License: MIT
  - Source: https://github.com/openai/openai-python

### Translation
- **deep-translator** - Translation services
  - License: MIT
  - Source: https://github.com/nidhaloff/deep-translator

## Original Implementation
The core application logic, UI design, real-time processing pipeline, and AI coaching system are original implementations created specifically for this TelePrompter project.

### Key Original Components:
- Real-time audio processing and transcription workflow
- AI coaching suggestion system with context awareness
- Multi-language translation integration
- Session management and export functionality
- Streamlit UI design and user experience flow
- Error handling and fallback mechanisms

## Compliance Statement
All third-party libraries are used in accordance with their respective licenses. This project is for educational and demonstration purposes.

GitHub Events

Total
  • Public event: 1
  • Push event: 1
Last Year
  • Public event: 1
  • Push event: 1

Dependencies

requirements.txt pypi
  • ffmpeg-python >=0.2.0
  • numpy >=1.24.0
  • openai >=1.3.0
  • openai-whisper >=20231117
  • sounddevice >=0.4.6
  • streamlit >=1.28.0
  • torch >=2.0.0
  • torchaudio >=2.0.0
  • torchvision >=0.15.0