Listen to anything, anytime, leveraging AI.
Audiora is an AI-enhanced audio platform that transforms user preferences into personalized engaging audio experiences.
- 🎯 Personalized Learning: AI-driven audiocasts tailored to your preferences
- 🔊 Seamless TTS: Natural-sounding audio conversion
- 📚 Diverse Content: Wide range of topics from professional skills to self-improvement
- 📱 Mobile-First: Optimized for on-the-go learning
- ⚡ Continuous Playback: Seamless cross-device listening
- Python 3.8+
- pip (Python package manager)
- Get your LLM Api keys - Openai | Anthropic | Gemini
- Get your TTS Api key Openai | Elevenlabs
- Clone the repository:
git clone https://github.com/nwaughachukwuma/audiora.git
cd audiora- Install dependencies:
pip install -r requirements.txt- Set up environment variables in .env:
OPENAI_API_KEY="your-openai-api-key"
ANTHROPIC_API_KEY="your-anthropic-api-key"
GEMINI_API_KEY="your-gemini-api-key"
ELEVENLABS_API_KEY="your-elevenlabs-api-key"
APP_URL="http://localhost:8080"
API_URL="http://localhost:8585"- Launch the application:
streamlit run app.py- Enter a prompt or choose from examples for your audiocast
- Tell the AI your preferences over a chat sessionn
- Click "Generate Audiocast"
- Listen and enjoy your personalized audio content
- Python and Streamlit
- AI: Custom models for TTS and content generation
- Pydub for audio enhancements
- Fork the repository
- Create a feature branch (git checkout -b feature/amazing-feature)
- Commit changes (git commit -m 'Add amazing feature')
- Push to branch (git push origin feature/amazing-feature)
- Open a Pull Request
This project is licensed under the MIT License. See the LICENSE file for more information.
- VeedoAI: https://veedo.ai
- Email: chuks@veedo.ai
- Twitter: @ChukwumaNwaugha