Features
Voice-led conversational English tutoring
Adaptive AI that adjusts to child's level
Speech recognition for kids' pronunciation
Gamified learning with rewards
Offline mode for core lessons
Parent dashboard with progress insights
Safe, ad-free environment
Curriculum covering vocabulary, grammar, and storytelling
Gentle correction and positive reinforcement
198B-A11B mixture-of-experts architecture
Vision-language understanding and generation
Fast inference for agent tool-use tasks
Multi-turn function calling support
Large context window for agent loops
Open-source model weights on HuggingFace
Strong multimodal reasoning and visual QA
High throughput per GPU with sparse activation
Customizable system prompts for agent behavior
Low-latency callback API design
Step-2 1.5B-step reasoning model on GitHub
