Features
AI-powered conversational teacher using ChatGPT
Multilingual speech recognition for 40+ languages
Pronunciation feedback (beta, American English only)
Real-time grammar correction and feedback
Adjustable speech speed (fast or slow)
Click-to-explain word meaning in context
Translations for words and sentences
Transliterations for Chinese, Japanese, Korean, Thai, Greek
Suggestions for what to say next
Audio playback of all phrases
Roleplay real-life situations
Mini-classes for guided learning
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
