Show HN: Stable Audio 3 – one-shot sample generator (110gb download)

Post by tom-wal » Sun, May 31, 2026, 1:54 PM UTC

Post by tom-wal » Sun, May 31, 2026, 3:45 PM UTC

stevehiehn wrote: post #3

tom-wal wrote: post #2

As a sound engineer, I can't believe what I see - all these sas tools are amazing. Maybe I missed it in the readme file: This requires a API key from generative AI models i suppose ?

Assuming you don't own a sufficient GPU, there are prescriptive instructions to rent a GPU from runpod.io

Post by stevehiehn » Mon, Jun 01, 2026, 6:40 PM UTC

4tsarism wrote: post #5

Any thoughts on possibility of running the generation step on apple silicon via MPS instead of renting a cuda pod?