https://blog.landryzetam.net/tags/whisper/Recent content in Whisper on Landry Zetam - Tech BlogHugo -- gohugo.ioen-usSat, 20 Dec 2025 00:00:00 +0000https://blog.landryzetam.net/posts/transcripts-to-summaries-audio-pipeline/Sat, 20 Dec 2025 00:00:00 +0000https://blog.landryzetam.net/posts/transcripts-to-summaries-audio-pipeline/<p>Remember that audio transcription pipeline I built? Raw recordings flow in, get compressed, transcribed by Whisper, and stored as JSON. Great for archival, but 204 transcript files sitting on NFS storage aren&rsquo;t exactly useful. Today I&rsquo;ll show you how I completed the loop—automatically summarizing transcripts with an LLM and publishing everything to my Obsidian vault.</p> <hr> <h2 id="part-1-the-problem-with-raw-transcripts">Part 1: The Problem with Raw Transcripts</h2> <p>The original pipeline worked beautifully. Every morning, new transcripts appeared as JSON files:</p>https://blog.landryzetam.net/posts/audio-transcription-pipeline/Fri, 12 Dec 2025 00:00:00 +0000https://blog.landryzetam.net/posts/audio-transcription-pipeline/<p>Every day, raw audio recordings land on an SFTP server. By morning, they&rsquo;re compressed, transcribed, and stored as searchable JSON - all without human intervention. Here&rsquo;s how I built this pipeline on my homelab Kubernetes cluster.</p> <h2 id="the-problem">The Problem</h2> <p>I had a growing collection of audio recordings that needed transcription. Manual processing wasn&rsquo;t sustainable: download files, compress them, run through a transcription service, organize the output. This needed automation.</p> <p>The requirements were straightforward:</p>