gemini-teacher  by nishuzumi

Spoken English pronunciation correction assistant using Gemini

created 7 months ago
1,078 stars

Top 35.8% on sourcepulse

GitHubView on GitHub
Project Summary

This project provides an AI-powered English pronunciation tutor using Google Gemini. It's designed for English language learners seeking real-time feedback on their speaking, including pronunciation correction, grammar suggestions, and interactive dialogue practice.

How It Works

The system leverages Google Gemini for AI-driven pronunciation assessment and feedback. It captures user speech via microphone, processes it for real-time recognition, and then provides targeted guidance on pronunciation and grammar. The architecture supports intelligent scene switching for varied practice scenarios.

Quick Start & Requirements

  • Install dependencies: pip install -r requirements.txt
  • System requirements: Python 3.11+, microphone, internet connection.
  • Prerequisites: Gemini API Key (free tier available at aistudio.google.com/app/apikey). Optional ElevenLabs API Key for voice output.
  • Run: python starter.py

Highlighted Details

  • Real-time voice recognition and AI-powered pronunciation evaluation.
  • Grammar correction and scenario-based dialogue practice.
  • Targeted pronunciation guidance and intelligent scene switching.
  • Optional voice output via ElevenLabs API.

Maintenance & Community

  • Open to Issues and Pull Requests.

Licensing & Compatibility

  • License: MIT
  • Compatible with commercial use and closed-source linking.

Limitations & Caveats

The project requires specific system dependencies (like portaudio19-dev on Ubuntu/Debian) to be installed before Python dependencies. The ElevenLabs API key is optional but required for voice output features.

Health Check
Last commit

6 months ago

Responsiveness

1 day

Pull Requests (30d)
0
Issues (30d)
0
Star History
45 stars in the last 90 days

Explore Similar Projects

Feedback? Help us improve.