Ai

A small, practical Node.js CLI that takes an audio file, transcribes it with speaker labels, and produces an action-item summary — using Amaniva's transcription API instead of managing your own ML pipeline.

A follow-up to my Video Meeting Notes Extraction project. Self-hosting Whisper works, but GPU costs, ffmpeg/sentencepiece errors, and dated translation models add up. Here's how I replaced that pipeline with a single hosted API call.

This tool can be a game-changer for those frequently dealing with video meetings. By converting videos into useful, summarized, and translatable notes, it enhances accessibility and saves time. Happy coding, and here’s to more streamlined workflows