Originally published on April 24, 2023. I've been working on podAI for the past week. It's a podcast search engine that uses Whisper to transcribe podcasts. It took me a while to find a sustainable way to transcribe large amounts of audio with Whisper. I'm sharing my learnings here in case it's helpful for others.Cost ComparisonI'm using a g4dn.xlarge instance on AWS. This instance has 1 Nvidia T4 GPU, 4 vCPUs, and 16GB of memory. It costs $0.526 per hour. OpenAI char...