His agent transcribes his voice messages on his home server
He sends audio messages to his AI. It transcribes them locally on the graphics card in his home server, so his voice notes become text without leaving the house.
How it works
- He sends an audio message to the agent
- The agent transcribes it locally on his home server GPU
- Text comes back
Why it’s worth knowing
The whole pipeline runs on his own hardware: voice in, text out, no cloud in the loop.
Where it’s from
Summarized from a public post on njump.me. See the original ↗