Inspiration
We wished to make an AI-driven assistant that makes learning more engaging, accessible, and interactive using text and audio responses.
What it does
We wished to make an AI-driven assistant that makes learning more engaging, accessible, and interactive using text and audio responses.
How we built it
Humanize AI We used Streamlit for the UI, Gemini AI API for generating answers, and gTTS (Google Text-to-Speech) for converting responses to audio.
Challenges we ran into
1.Correctly handling API response formats. 2.Making sure text-to-speech conversion goes on smoothly. 3.Optimizing response speed for a smooth user experience.
Accomplishments that we're proud of
Effectively incorporating AI-created text and audio answers. Building an easy-to-use, user-friendly interface with Streamlit. Delivering learning in an accessible voice-based format.
What we learned
Delivering effective API integration for AI-enabled applications. Improving user experience with multi-modal (text + sound) outputs. Debugging and AI response generation optimization.
What's next for EchoMind : AI Learning Assistant
Adding multilingual capability for global accessibility. Enriching voice output with natural-sounding AI voices. Adding chat history and customized learning capabilities. Expanding to a mobile app for learning on the go
Built With
- io
- languages:-python-frameworks:-streamlit-apis:-gemini-ai-api-libraries:-gtts-(google-text-to-speech)
- platforms:
- requests
- web-based
Log in or sign up for Devpost to join the conversation.