Paste a meeting transcript (from speech_to_text or manual notes) and receive a clean summary with key decisions, action items, and follow-up dates. Great for quickly turning hour-long discussions into shareable minutes. Works best when you include speaker attribution and timestamps in the input. Maximum context window (input and output combined): about 1,048,576 tokens. Maximum output per reply: about 65,536 tokens (model reasoning, if any, counts toward this limit). Output content formats: Text This module does not support continuous conversations. AI can make mistakes. Please verify important information.