Frequently asked questions

The app uses Whisper-powered speech recognition to transcribe spoken questions during practice sessions. It captures your microphone input for accurate transcription.

No. All API keys are built in. Free plan uses Mercury 2.5 (the default), GPT-OSS 120B (on Cerebras and Groq) and Qwen. Pro adds Gemini 2.5 Flash-Lite and GPT-6 Luna; Pro+ adds Claude Haiku 5.5 and Gemini 3 Flash — no extra charges.

Free models — Mercury 2.5 (the default, near-instant), GPT-OSS 120B on Cerebras and Groq, and Qwen — are fast and great for most interviews. Pro adds Gemini 2.5 Flash-Lite and GPT-6 Luna. Pro+ unlocks premium models like Gemini 3 Flash and Claude Haiku 5.5. See the full breakdown on our pricing section.

Yes. Available for both Windows and macOS. Download the version for your OS from the download section.

Yes. Cancel anytime. Access continues until end of billing period. No questions asked.

Yes. We offer a 14-day money-back guarantee on your first payment on a new subscription, as long as your account has used less than 30 minutes of live session time since that payment. If you’re not satisfied, contact support@copilotinterview.com within 14 days of your first payment for a full refund. You can see your live session time in your account dashboard. Renewal charges and your statutory rights are described in our Refund Policy.

Yes. Audio is captured on your machine and streamed in short encrypted segments through our proxy to a speech-to-text model (Groq Whisper); only the transcribed question and the context you entered go to the AI model you chose. Nothing is kept on our servers beyond the request itself — we never store your interview audio, transcripts, or answers. Your session files are saved to your own Documents folder. If you leave anonymous question stats on, the question titles, categories and scores from a 📊 Summary are shared (never answers, transcripts or personal details); the toggle is under every report and in Options.

A structured answer appears in about 2 seconds after the question ends, because live transcription has already run in the background by the time you click. Fast free models and premium models land in roughly the same window.

Yes — that's what Mock Interview mode is for (desktop app 1.3.11 and later). Paste the job description and your résumé; the AI builds a tailored set of behavioral, technical, system-design and coding questions, reads each one aloud, listens to your spoken answer and grades it with a score, what to fix, a model answer and the follow-up a real interviewer would ask. Coding questions get a code box. The round ends with a report card. It's on the free tier too. Interviewer Mode is the counterpart for people running interviews.