Skip to content

audio-in-text-out.mdx #30

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
nwthomas wants to merge 1 commit into from
Closed

audio-in-text-out.mdx #30

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
20 changes: 20 additions & 0 deletions app/(writing)/content/audio-in-text-out.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
export const metadata = {
title: "Audio In, Text Out",
description: "Predicting the future of AI UX and model use",
openGraph: {
title: "Audio In, Text Out",
description: "Predicting the future of AI UX and model use",
},
};

> I haven't normally written _predictive_ articles. However, I spent most of the last 3 years telling people that taste was all that would matter in the future thanks to new AI advances (and, in mid-2022, got weird looks). This is now standard discourse on social media.
>
> I want to put down a similar prediction for posterity.

Current AI LLM model chat UI/UX is byzentine. Additionally, nobody has nailed a voice mode yet. Typing out content to the model feels like you're doing homework, and listening to the model's speach response feels like sitting in timeout.

If you've ever used visual voicemail on your phone, you'll know how nice it is to be able to read the audio out. In fact, I'd be willing to be that you seldom actually listen to the audio if the transcription seems accurate.

Humans generally speak faster than we type and read faster than we can listen. I predict that the future optimal UX of AI models (LLM or otherwise) will be audio in, text out. For those who really want it, interfaces should have optionality to toggle back on audio (speech) responses.

This format solves the major pain points of interacting with AI models, primarly feeling like you're having to slow down in order to do your best work.
8 changes: 7 additions & 1 deletion app/(writing)/posts.json
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,11 @@
{
"posts": [
{
"id": "audio-in-text-out",
"title": "Audio In, Text Out",
"description": "Predicting the future of AI UX and model use",
"date": "2026-03-19"
},
{
"id": "strange-faces",
"title": "Strange Faces",
Expand All @@ -16,7 +22,7 @@
"id": "local-models",
"title": "Local Models",
"description": "Learn how to run your own AI models locally",
"date": "2026-01-16"
"date": "2026-02-25"
},
{
"id": "simple-is-hard-enough",
Expand Down