signalDEV Community2026-10-03
ColdMock: Building an Autonomous, Zero-Cost Voice Interviewer for My College Peer
ColdMock is a free, browser-based voice interviewer that runs fully offline using Google Gemma 2B via Ollama. It conducts oral technical drills with automatic 5-second silence submission, unscripted follow-ups, and a final scorecard. In a test, it challenged a friend's use of read replicas by asking about replication lag, while keeping all audio and notes local.
- for who
- College students preparing for technical interviews who freeze up when explaining systems concepts out loud.
- why now
- Hacktoberfest's live challenge makes this zero-cost, offline voice interviewer timely for students now.
- what changes
- They can practice oral technical drills anytime, anywhere, without subscription fees or cloud delays, and get realistic pushback instead of generic praise.
- to do
- Clone the ColdMock repository from GitHub and run it locally with Ollama to start zero-cost voice interview practice.
key points
- Runs entirely in-browser with Google Gemma 2B via Ollama, no internet needed
- Uses Web Speech API for voice, FastAPI for grading, auto-submits after 5 seconds of silence
- Test drill on database locks challenged a read replica choice with replication lag
#voice interview#ai education#open source tool#offline ai3 sources · confidence medium
score
score 8 out of 10. 0-10: how dense the facts are, multiplied by how much you can do with them after reading. 8+ means the topic's evidence bar is met: benchmarks and availability for a new model, amount and investors for a funding round, revenue figures for a solo-money story. Below 5 an item does not enter the digest. A press release scores 3 or less, a reprint loses 2, anything older than 14 days loses 1, a headline that misleads loses 3.
read the source