DEV Community

Masih Maafi
Masih Maafi

Posted on

I Built a Local, GPU-Accelerated Voice Commander—And I Still Type Everything

#ai #programming #productivity #python

I Built a Local, GPU-Accelerated Voice Commander—And I Still Type Everything

As developers, we love building productivity tools. We spend days optimizing our development environments, writing shell scripts, configuring keybindings, and building custom pipelines.

A few months ago, I built Voice Commander—a local, GPU-accelerated voice transcription system. It uses a local CUDA-powered Whisper.cpp model to transcribe my speech, and hooks into the Gemini API to clean up filler words ("um", "uh"), fix grammar, structure the output, and auto-paste it directly at my cursor.

It works like a charm. It is fast, private, and precise.

And yet, I still type everything.

Every time I need to write a long code comment, draft an issue, or even outline a plan, my hands immediately go to the keyboard. I catch myself typing away, while the microphone hotkey is right there, ready to save me hundreds of keystrokes.

Why is this? And why is it so hard to break the keyboard habit?

The Psychological Friction of Voice Coding

Through this, I realized that typing isn't just a physical action; it's a cognitive buffer.

  1. The Fear of Speaking Aloud: There is a strange, uncomfortable awkwardness in talking to an empty room. When we speak, it feels like a performative act. Writing, on the other hand, is silent, internal, and feels like direct translation of thought.
  2. Editing While Thinking: When we type, we edit continuously. We delete a word, rewrite a sentence, and pause mid-sentence. Speaking requires us to formulate a complete thought before opening our mouth, which feels like a higher cognitive load.
  3. Muscle Memory: Our fingers have years of muscle memory trained to hit keys. Overriding that reflex with a vocal cue requires active willpower.

Building the Habit

Refusing to use a tool you built because it "feels weird" is a common trap. To break this, I'm forcing myself to follow a new rule: if a thought requires more than two sentences, I must dictate it.

By pushing through the initial awkwardness, I'm hoping to make voice-to-text as natural as reaching for the trackpad.

Have you built tools that you struggle to integrate into your actual daily routine? How do you overcome the muscle memory of typing?

If you want to try out the project locally, check it out on GitHub: *MasihMoafi/Voice-commander***

For more of my AI research and developer tools, visit my website: *masihmoafi.tech***

Top comments (0)