AI Micro-Internship · ~240 min · builder
Build a lecture-audio → structured-notes tool
Speech-to-insight tools are everywhere in 2026 workplaces. Build your own: record real audio (a class, a YouTube lecture, a family explanation — with consent), transcribe it with a free speech-to-text model, and turn the transcript into structured notes automatically.
Steps
- 01Get 2 real recordings with consent (10+ minutes total): a class, a study-group session, or a lecture you play and record.
- 02Build the pipeline: audio → transcription (Whisper locally/Colab, or Gemini’s audio input) → LLM pass that structures it into topics, key points, and action items.
- 03Compare output against the actual audio: mark transcription errors (Indian accents and Hinglish will produce them) and structure mistakes.
- 04Fix the worst failure mode with prompt or code changes, and push everything to a public repo.
Tools: Whisper (free, Colab) or Gemini audio, An AI coding assistant, GitHub, Consented real audio
Your submission
Submit the repo, a demo video of the pipeline running, one full before/after (raw transcript → structured notes), and the accuracy audit.