September 1, 2025
I heard you like TUIs.
Here's a TUI for the gpt-realtime voice dictation stuff I posted last week. Also a gpt-5 version. And a local @pipecat_ai transport for macOS with acoustic echo cancellation.
I'm having a lot of fun blurring the boundaries between voice dictation and using an LLM as a full natural language assistant. I *definitely* do not have the prompting right, yet, to be able to talk completely free-form to the LLM and have it dictate the right text to the right window every time.
Things work a lot of the time. You get used to a certain level of magic happening. And then a command will fail in a surprising way.
If I were building this for production use I would lock down the behavior a lot. I would try to build a mostly deterministic set of input->output flows on top of the (valuable) non-deterministic LLM substrate.
But actually experimenting with this jagged frontier is interesting and useful as a learning experience.
Code[1]
Both the macOS transport and the tui components were mostly written by codex cli. I have a lot of messy code in various repos that collectively do most of the things I want to do for a project like this. So I've been pointing codex at old code and…