https://github.com/dervinevolve/empathyarchives

https://github.com/dervinevolve/empathyarchives

Last synced: about 1 month ago
JSON representation

• Host: GitHub
• URL: https://github.com/dervinevolve/empathyarchives
• Owner: DervinEvolve
• Created: 2024-09-16T22:47:54.000Z (4 months ago)
• Default Branch: main
• Last Pushed: 2024-09-18T01:07:31.000Z (4 months ago)
• Last Synced: 2024-09-18T06:05:44.739Z (4 months ago)
• Language: TypeScript
• Homepage: https://empathyarchives.vercel.app
• Size: 2.08 MB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        


  
Empathy Archives

  
Your Historical Research Assistant


  



## Overview

Empathy Archives is an innovative voice-to-voice interface designed for students and educators to engage in intuitive conversations about history. This project was developed as a submission for Microsoft's Hackathon, leveraging the power of Hume AI's expression detection models to create a more empathetic and responsive learning experience.

## Features

- **Voice-to-Voice Interaction**: Engage in natural, spoken conversations about historical topics.

- **Emotion-Aware Responses**: The AI adapts its output based on the user's tone, creating a more personalized interaction.

- **Primary Source Integration**: Access and discuss a vast array of historical primary sources.

- **Real-time Transcription**: View a live transcription of the conversation.

- **Tone Analysis**: Displays the top three detected tones in the user's voice output.

## How It Works

1. **User Input**: Speak your question or topic of interest related to history.

2. **Voice Analysis**: Hume AI's expression detection models analyze your tone and emotion.

3. **Contextual Search**: The AI searches for relevant primary sources and historical information.

4. **Tailored Response**: Based on the analysis and search results, the AI formulates a response.

5. **Expressive Output**: The response is delivered via voice, with tone and pacing adjusted to match the context.

6. **Visual Feedback**: A transcription appears on screen, highlighting the detected tones.