Cheetah is an AI-powered macOS application designed to assist users during software engineering interview practice through real-time coaching capabilities. It integrates audio transcription and AI-generated responses to help users navigate technical interview questions as they happen. Cheetah uses a local speech-to-text engine based on Whisper to capture and transcribe conversations in real time, enabling it to understand interviewer prompts. It then leverages language models to generate suggested answers, refinements, or explanations tailored to the ongoing discussion. Cheetah also connects with live coding environments through a browser extension, allowing it to analyze code and logs directly from supported platforms. Cheetah provides simple controls for generating answers, refining responses, and analyzing technical output, making it interactive during mock interviews.
Features
- Real-time audio transcription using a locally running speech model
- AI-generated answers to interviewer questions during sessions
- Refinement tool to iteratively improve generated responses
- Code and log analysis via browser extension integration
- Live coding platform support through a Firefox extension
- Simple interface with dedicated actions for answer, refine, and analyze