Features
Immersive AI voice chat with dialect selection
Daily articles with comprehension questions
Click-to-learn vocabulary in context
Instant corrections and step-by-step guidance
Personalized level, interest, and pace adaptation
24/7 availability for flexible practice
Judgment-free speaking environment
Vocabulary building with spaced repetition hints
Progress tracking across sessions
Mobile app and browser access
18+ supported languages including English, Spanish, German, Japanese, French, Mandarin, Russian, Korean
Multiple dialect tutors per language
AI tutor discusses article content
Real-life scenario immersion
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
