Summary

Immergo is an immersive language learning application simulating real-world roleplay scenarios, powered by the Google Gemini Live SDK. It targets language learners seeking to practice conversational skills with an AI acting as a native speaker, offering a low-latency, interactive environment with immediate feedback to accelerate fluency.

How It Works

The system leverages the Google Gemini Live SDK for real-time, multimodal interaction. A Python FastAPI backend manages AI communications via WebSockets, while a Vanilla JavaScript frontend handles the UI and audio streaming. It simulates authentic scenarios with proactive AI personas, supporting structured "Immersive Mode" (strict target language) and "Teacher Mode" (explanations/translations), alongside performance scoring.

Quick Start & Requirements

• Installation: Clone repo, run ./scripts/install.sh, configure .env.
• Prerequisites: Node.js (v18+), Python (v3.10+), Google Cloud Project with Vertex AI, configured ADC.
• Deployment: One-click Google Cloud Run deployment available. Local dev via ./scripts/dev.sh or production build.
• Demo: immersive-language-learning.app.

Highlighted Details

• Learning Modes: "Immersive Mode" for strict practice, "Teacher Mode" for guided learning.
• AI Personas: AI adopts specific, proactive roles and communicates contextually.
• Performance Feedback: Fluency grades (Tiro, Proficiens, Peritus) and actionable feedback provided.
• Google Antigravity: Enables rapid feature iteration and UI customization via natural language prompts.

Maintenance & Community

No specific details on maintainers, community channels, or project roadmap were found in the provided README.

Licensing & Compatibility

The README does not specify a software license, preventing an assessment of commercial use or closed-source integration compatibility.

Limitations & Caveats

Heavy reliance on Google Cloud services (Vertex AI, Cloud Run) requires a Google Cloud Project and credentials. Usage incurs costs based on Google Gemini Live API pricing (estimated ~1.7 cents/minute). The absence of a stated license is a significant adoption blocker.