Voices

Inspiration We know that many introverted people are afraid of public speaking, therefore we develop a platform that allows you to practice your skills without any worry thanks to fish audio. The ability to speak to people in a variety of situations is necessary because you can't always have a script for everything. With our platform, we create scenarios that are likely to occur in real life, but you don't have to worry about what other people think of you because we'll tell you how you perform and provide professional advice for your social life and career. We are aware that having a conversation is difficult and that many people lack the courage to just speak more, this is why this project is born.

What it does This is the Ultimate Public Speaking Scenario Practice Platform, with just a click and you can summon our AI chat agent to practice your public speaking skill with you, this project gives users both and environment to practice and an AI-powered public speaking coach, one that talks back, evaluates performance, and helps you get better at real-world conversations and presentations.

How we built it We build it using SnapDev, creating the foundation with NextJs. Then, we created our voice agents with Fish Audio creating different agents for different scenarios. Then, we used Gemini to extract and analyze content put in by the user so the voice agents could create targeted questions related to the material.

Challenges we ran into We ran into multiple challenges trying to mimic conversational scenarios with our voice agents and the transcription from the mic.

Accomplishments that we're proud of We're proud of having differently calibrated voice agents suited to each scenario the user wants to use.

What we learned We learned how to integrate and implement new technology using documentation and AI. We learned how to properly code and program in collaboration with AI, using AI technologies like Cofoundry.

What's next for Voices Implement more scenarios in which the user could practice Smoothen out the flow between the voice agents and user conversationally Store the transcriptions on the cloud instead of locally.