Skip to main content

Welcome to SvaraAI Documentation

Build emotion-aware voice therapy experiences with real-time emotion detection and AI-powered therapeutic feedback.

Quick Start

Get SvaraAI up and running in minutes

1

Clone the repository

Clone the SvaraAI repository to your local machine:
git clone https://github.com/whysooharsh/svaraAI.git
cd svaraAI
2

Set up environment variables

Create .env files in both Frontend and Backend directories with your API keys:Frontend/.env
VITE_HUME_API_KEY=your_hume_api_key
VITE_HUME_CONFIG_ID=your_hume_config_id
Backend/.env
VITE_HUME_API_KEY=your_hume_api_key
HUME_SECRET_KEY=your_hume_secret_key
GEMINI_API_KEY=your_gemini_api_key
GEMINI_PROMPT=your_therapeutic_prompt_template
You’ll need API keys from Hume AI and Google Gemini.
3

Install dependencies and run

Install dependencies for both frontend and backend, then start the development servers:
# Backend
cd Backend
npm install
npm run dev

# Frontend (in a new terminal)
cd Frontend
npm install
npm run dev
The frontend will be available at http://localhost:5173 and the backend at http://localhost:5000.
4

Start a conversation

Navigate to the playground at /playground and click the microphone button to start a voice conversation. SvaraAI will detect your emotions in real-time and provide therapeutic feedback.
After your conversation, visit /insights to view detailed emotion analytics and AI-generated insights.

Explore by Topic

Learn about SvaraAI’s core capabilities

Voice Emotion Detection

Real-time emotion detection from voice using Hume AI’s prosody analysis

Therapeutic Feedback

AI-powered therapeutic responses generated with Google Gemini

Conversation Insights

Detailed emotion analytics and conversation history

Architecture Overview

Understand how SvaraAI’s frontend and backend work together

Key Features

What makes SvaraAI powerful

Real-time Voice Analysis

Detect emotions from voice in real-time using Hume AI’s advanced prosody and language models

Intelligent Feedback

Get personalized therapeutic responses powered by Google Gemini’s AI

Emotion Analytics

Track emotional patterns over time with detailed conversation insights

Voice Chat Interface

Natural voice conversations with visual emotion display and FFT visualization

Ready to get started?

Follow our quickstart guide to set up SvaraAI and start building emotion-aware voice experiences.

View Quickstart Guide