Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .gitignore
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
# Environment variables
.env
# Python cache
__pycache__/
*.pyc
80 changes: 80 additions & 0 deletions AI_Voice_Agent.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,80 @@
# Open Source Hackathon 2026 Project Submission

## Participant Details

**Full Name:**
Saloni Sharma

**GitHub Username:**
Saloni90Sharma

**Team Name:**


**College/University:**
GLA University Mathura

---

## Project Details

**Project Title:**
AI Voice Agent

**Project Description:**
AI-powered voice assistant built with FastAPI, Google Gemini 1.5 Flash, and Web Speech APIs, featuring real-time voice interaction, conversation memory, and natural speech responses.

**Tech Stack Used:**
Frontend: HTML5, CSS3, JavaScript
Backend: Python, FastAPI, Uvicorn
AI Model: Google Gemini 1.5 Flash
Speech Recognition: Web Speech API
Text-to-Speech: SpeechSynthesis API
Deployment: Render, GitHub

**GitHub Repository Link:**
[<!-- Add your public project repository link -->](https://github.com/Saloni90sharma/AI_Voice_Agent_Project.git)

**Live Demo Link:**
<!-- Add deployed link if available -->

**Presentation / Demo Video Link:**
<!-- Optional but recommended -->

---

## Open Source Readiness

- [βœ“] My project is public on GitHub
- [βœ“] My repository has a proper README.md
- [βœ“] I have added setup/installation instructions
- [βœ“] I have added screenshots/demo where possible
- [βœ“] I have added a license file
- [βœ“] My project is original and built/updated during the hackathon period

---

## Memori Labs Sponsor Task

Please complete these before submitting:

- [βœ“] I have starred the Memori Labs GitHub repository
https://github.com/MemoriLabs/Memori

- [βœ“] I have followed Memori Labs on LinkedIn
https://www.linkedin.com/company/memorilabs/

- [βœ“] I have followed Memori Labs on X
https://x.com/memorilab

- [βœ“] I have checked Memori Labs social links
https://linktr.ee/memorilabs

---

## ID Card Verification

- [βœ“] I have generated my ID card from https://oshack.xyz
- [βœ“] If my ID was not verified, I completed the mandatory verification/giveaway form and tried again

---
102 changes: 102 additions & 0 deletions README.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,102 @@
# πŸŽ™οΈ **AI Voice Agent with Chat History**
πŸš€ *Day 10 of my AI Voice Agent Challenge*

> πŸ—£οΈ Talk to AI, have a real conversation, and get human-like voice replies β€” **with memory**!

---

## ✨ **Features**
βœ… **Voice Input** β€” Speak directly to the AI agent
βœ… **Conversation Memory** β€” Remembers past messages in the same session
βœ… **Smart Responses** β€” Powered by Google Gemini LLM
βœ… **Natural Voice Output** β€” Murf AI TTS for lifelike speech
βœ… **Lightweight UI** β€” Plain HTML, CSS, JS (no heavy frameworks)

---

## πŸ— **Architecture**

🎀 Your Voice
⬇
πŸ“ AssemblyAI (Speech-to-Text)
⬇
βš™οΈ Python FastAPI Server (Stores Chat History)
⬇
🧠 Google Gemini (LLM)
⬇
πŸŽ™οΈ Murf AI (Text-to-Speech)
⬇
πŸ”Š Audio Response


---

## πŸ›  **Tech Stack**
| Layer | Technology |
|----------------|------------|
| **Backend** | Python, FastAPI, Uvicorn |
| **Frontend** | HTML5, CSS3, JavaScript |
| **STT** | AssemblyAI API |
| **LLM** | Google Gemini API |
| **TTS** | Murf AI API |

---

## ⚑ **Quick Start**

### 1️⃣ Prerequisites
- Python **3.9+**
- API Keys:
- `ASSEMBLYAI_API_KEY`
- `GOOGLE_GEMINI_API_KEY`
- `MURF_API_KEY`

### 2️⃣ Environment Variables
Create a `.env` file in the project root:

```env
ASSEMBLYAI_API_KEY=your_assemblyai_api_key
GOOGLE_GEMINI_API_KEY=your_gemini_api_key
MURF_API_KEY=your_murf_api_key

### 3️⃣ Install Dependencies
pip install -r requirements.txt

# Backend Framework
fastapi
uvicorn

# API Calls & Utilities
requests
python-dotenv

# Audio Handling
pydub
soundfile
numpy

# STT (Speech-to-Text)
assemblyai

# LLM (Google Gemini)
google-generativeai

# TTS (Text-to-Speech - Murf AI via API calls)
# No official Python SDK, handled via requests

# Optional Dev Tools
black


### 4️⃣ Run the API Server
uvicorn main:app --reload

### 5️⃣ Open the Frontend

Open frontend.html in your browser with a session_id:
http://127.0.0.1:5500/frontend.html?session_id=abc123

πŸ† Author

πŸ‘¨β€πŸ’» Saloni Sharma β€” AI Developer & Voice Tech Enthusiast
πŸ“Œ 13th Part of my 30 Days of AI Voice Agents series
75 changes: 0 additions & 75 deletions Submission/PROJECT NAME.md

This file was deleted.

Loading