# Voice is Underutilized


Speech is a useful medium for communicating with AI, both as an input/output
channel and as back-and-forth. Over 2026 I’ve been increasing the amount of
speech I/O and have collected a fair number of use cases.

### Input

Voice is, of course, great for rambling at coding agents. Oftentimes the
transactional “just talking with the agent” convo stuff is easier to ramble out
than it is to type. I also occasionally have wrist sensitivity issues that make
it difficult to type -- now with STT and computer-use, that’s not a hassle.
(Knock on wood about RSI 😬)

Voice is also good for capturing context. Every phone has a voice recorder on
it; most meeting software now has transcription support. There’s a lot of
ambient context that just exists in conversations that, if you can
(consentingly) capture it, has a ton of downstream value. For example: my team
has been transcribing design syncs consistently. A few solo agent sessions
interspersed between transcribed design syncs allow engineers to iterate on
designs quickly without having to do the “sit down for several hours and write a
doc” schtick.

Earlier in the year, my team had an onsite where we got a few folks into the
room and hammered out long-term plans. Those conversations were fully
transcribed and have been instrumental in a bunch of the work I ended up doing
later in the year. Having the context in textual form “froze” those ideation
sessions, allowing me to rehydrate them months later, when I had cycles to think
about the problems discussed again. That being said, there are obviously some
things that you don’t want recorded, for one reason or another. In practice,
it’s much more common for us to regret not having transcribed a meeting than the
other way around.

Voice input also allows you to write thoughts or capture things that you
wouldn’t otherwise have time to do. For instance, I often now ramble into the
Voice Memos app on my phone while commuting home about a problem I’m thinking
about, with a few proposed sketches of a solution -- just pure
stream-of-consciousness. Then when I get home, I transcribe the audio, set an
agent up on it with `/goal` overnight, and come back to find (surprisingly
often) the problem fully solved.

**Models**: Local STT models are excellent. I’ve been using
[FluidVoice](https://github.com/altic-dev/FluidVoice), with NVIDIA’s
[Parakeet models](https://catalog.ngc.nvidia.com/orgs/nvidia/-/collections/parakeet-tdt-0.6b/-),
and it’s remarkably accurate. Claude/ChatGPT are good at cleaning up
transcription errors. Parakeet + FluidVoice + a Claude Opus cleanup is nearly
indistinguishable from 100% accurate for my use cases.

### Output

Since early this year, I’ve been building and tweaking a personal daily briefing
“podcast” which aggregates a bunch of information sources I care about, and uses
a text-to-speech model to make a daily audio briefing.

This briefing contains things like:

- Local/national/international news, stock market conditions
- Aviation weather on days I go flying
- Tasks due today, calendar events
- Summaries of articles in my RSS feed reader
- Generated research segments about topics inferred as likely to be interesting
  to me based on recent personal context (using [Exa](https://exa.ai/) for
  research)
- Local nature “news”, like the timing of bird migrations, salmon runs, and
  blooms
- Local concerts and cultural events
- Astronomical events, such as the visibility of planets and meteor showers

It’s generally 10-20 minutes of audio daily. I tweaked it for a couple months to
get it exactly how I like it, and now the quality is consistently high. The
crucial, and most difficult, part of this was building enough variety into the
“schedule” of what segments show up in the briefing every day that it doesn’t
end up sounding stale, gimmicky, or formulaic.

A simple “Claude, give me a daily briefing” becomes stale after a few days. You
really do need entropy and novelty and continuously updating/streaming context
for this sort of thing to be consistently interesting.

But now it _is_ quite interesting to me! It’s made me significantly more aware
of local news, and has allowed me to “read” more of the RSS feeds that I
subscribe to -- especially articles which I likely wouldn’t have read due to the
title not being interesting, but which the LLM thought were interesting based on
its actual contents and knowledge of my interests.

Output is also handy for learning things with LLMs. Earlier this year I set up a
system for generating “explainers” as podcasts, and learned quite a bit about
aviation, various distributed systems topics, and other areas of interest
through passive audio consumption.

**Models**: I had been using GPT-4o mini TTS as my “programmatic output voice
model of choice” for quite a while until its deprecation was announced
([RIP](https://developers.openai.com/api/docs/deprecations#2026-10-01-text-to-speech-models)).
I’ve now switched to
[Gemini 3.8 TTS](https://blog.google/innovation-and-ai/models-and-research/gemini-models/gemini-3-8-text-to-speech/),
and it’s _fantastic_. It features expressive voices, works over OpenRouter, and
is cheap. Highly recommended.

### Interactive / Real-time

Claude, ChatGPT, and Gemini all have a “live” interactive voice mode -- where
you can conversationally talk with the model, and it can respond and take
actions using tools, and so on. The primary time I use the interactive mode is
during commutes. It’s helpful to use the voice mode to triage tasks, ask
research questions, and iterate on ideas. It’s like taking time that would
otherwise be dead time and translating it into something that can be productive.

Voice is also convenient for walking around the house and capturing things that
need to happen. As you remember things, you can have the AI make tasks or
calendar entries and burn through a bunch of administrivia without interacting
with your phone. It’s like having an actual, literal assistant.

My preferred model is Claude for voice interactive mode (even though it’s not a
“native” voice-to-voice model like ChatGPT). A while back the Claude voice mode
added support for using MCPs, and that was a game changer.[^chatgpt] I’ve built
a whole [personal set of software](/blog/2026/11/02/Interpolative-Software/)
that has everything from tasks to notes to flashcards, all of which is
accessible through MCP. The ability to use MCP via voice means that I can use
the live voice mode for triaging or quickly recording tasks.

I also use it for reviewing flashcards. Since my MCP supports flashcards, I can
have Claude ask me questions, I have to give the answer, and then the model
grades my answer and records it. This is, in my opinion, strictly better than
the normal Anki app, because with Anki, you can flip through cards quickly and
semi-trick yourself into thinking that you actually know the answer. But if
you’re forced to say it out loud: one, doing it verbally can help retention, in
my opinion. And two, you are actually being graded. You’re not just in your mind
thinking, “Oh yeah, I know how to do this.”

When the models got access to web search through the voice mode, for months all
I was doing was asking research questions about history or technology or
anything that I was interested in, and having conversations about it. It’s a fun
rabbit hole tool.

Back in the GPT-4o days, you had to take anything it said with many grains of
salt, and you still have to do that now. But if you use Opus, you can generally
trust what it says in the voice mode, even though the voice modes tend to still
lag behind the normal text modes in features, and you tend to be stuck on the
older, worse models for a couple weeks before they upgrade them, even when
everything else in the product is seemingly over on the new models.

---

**TL;DR**: voice is underutilized! It’s a natural modality, and it’s
“programmable” at this point. I’d suggest trying, if nothing else, the “on my
commute I record Voice Memo prompts or talk with the model about
tasks/interests/etc.” I’ve already converted a few people to this and have
received positive reactions. Make your own bespoke personal audience-of-one
podcast, listen to articles you wouldn’t have time to read, record a brain dump
and then have an LLM help you pick through it. There’s a ton of mundane utility
to be had.

[^chatgpt]:
    I recall ChatGPT added this support recently too, but in my testing it was
    somewhat inconsistent, and I had already standardized on using Claude for
    this use case, which has been sticky.