Drop an episode and get timestamps, chapter titles and show notes
Intermediate16h1–3
WhisperEmbeddingsLLM
16/20Mock Interview Voice Coach
Practise a spoken interview and get feedback on answers, pace and filler words.
Intermediate18h1–3 people17/20 fit
Build Mock Interview Voice Coach for students preparing for placements in ~18h with 1–3 people. Stack: Whisper + LLM + TTS + Next.js.
Why it wins: Every student judge has been through this, so the pain is shared.
Build flow
01 · Problem
Students rarely get realistic interview practice and nobody tells them they say 'basically' 40 times.
02 · Solution
Generate role-specific questions, record spoken answers, transcribe them, score structure with a STAR rubric and count filler words and speaking pace.
03 · Build
- 1Generate questions from a job title
- 2Record and transcribe answers
- 3Score with a STAR rubric prompt
- 4Compute words per minute and fillers
04 · Demo
Answer one question live and show the filler-word count and rewritten answer.
MVP checklist
- Role-based questions
- Voice answers
- STAR feedback
- Filler and pace stats
Tech stack
| Tech | Role | |
|---|---|---|
| Whisper | Speech-to-text | AI |
| LLM | Language model | AI |
| TTS | Text-to-speech | AI |
| Next.js | Frontend + API routes | Web |
Reference repos
Open-source projects you can build on. Links checked 2026-10-31.
Related ideas
More AISee where in a call the customer got frustrated and why
Intermediate16h1–3WhisperLLMCharts16/20Upload a rental agreement and see risky clauses explained in plain language
Intermediate14h1–3PDF.jsLLMNext.js16/20