Inspiration
We wanted to help deaf and mute individuals express emotions through voice, not just text, making digital communication feel more human.
What it does
HearMeNow converts typed text into expressive, natural sounding speech with emotional tone options like happy sad calm or urgent.
How we built it
We built a simple web app using React for the frontend and Node.js for the backend. The ElevenLabs API powers the emotion-based text-to-speech, connected through WebSockets for real-time output.
Challenges we ran into
We struggled with syncing audio playback timing, handling real-time streaming, and fine tuning emotion control for more natural-sounding voices.
Accomplishments that we're proud of
We created a working prototype that gives people with speech impairments an expressive voice and demonstrated seamless real-time emotional speech generation.
What we learned
We learned how to integrate AI voice APIs, manage real-time data flow, and design with accessibility and emotion in mind.
What's next for HearMeNow
iOs development as well as multilingual text to speech.
Built With
- api
- git
- github
- json
- n/a
- node.js
- react-native
- tailwind
- vite
Log in or sign up for Devpost to join the conversation.