
Dictation that works with VoiceInk
A while back, I started using Neovim. I wanted to code faster. I began learning vim motions. It took some time, but I got better. Overall, I was really happy with the experience. I started with nvchad.com, and I’ve learned a lot. If you haven’t tried it, I highly recommend it. It’s easy to get started.
One day watching a coding video, realized I type very slow. My speed is about 50 to 60 words per minute. I often look at the keyboard to find keys, which is basically a rookie mistake. To improve, I started training on monkeytype.com. I practiced one or two times a week. It was helpful. Now, I don’t look at the keyboard much. But I still wanted to type faster.
Discovering SuperWhisper
Then I discovered SuperWhisper. It’s an app for dictation. It uses voice models, and it works great! You just speak, and it gets everything right. I love that it ignores filler words like “uuuuhm”. It just gets the text right. Whatever it was doing under the hood was not my business.
However, there’s a downside. It’s expensive. It has a monthly fee. There’s a “pay once” option, but it’s overpriced. So, I looked for alternatives and found VoiceInk. That’s what I’m using to write this blog post now!
VoiceInk Experience
I’m amazed by VoiceInk. It took some time to learn its features. But with a bit of setup, it’s fantastic. Right now, I’m speaking to my computer! I created a custom prompt for blogs. It includes instructions like:
- Be concise
- Don’t use complicated words
- Remove fillers
The process is simple. First, it uses a local model to transcribe audio to text. Then, that text goes to OpenAI with my prompt. It’s seamless! I’ve been talking for two or three minutes, and I get nice text without needing much corrections. The OpenAI pass is not really necessary if you want to skip it but in this case it will give my dictation the correct formatting for a blog post. I just use the local dictation module most of the time.
It also lets me add custom vocabulary. I can talk about different technologies or weird words, and it picks it up.
The Weirdness Factor
It still feels strange though. I feel a big weirdness when using it around other people. I try to use it when my girlfriend is not around. We just laugh when she comes in and I’m talking to my computer, but still. Haven’t been able to get past that. Guess it’s another win for remote work. Can’t even imagine a whole office with people using voice dictation.
So, I just wanted to share my experience. I’m super happy with this setup!
Here’s my blog post prompt that is sent to OpenAI to do a small fixing to my dictation.
Edit this text with this primary rules in mind:
1. Maintain a casual tone.
2. Avoid complex words.
3. Prefer short sentences. avoid commas.
4. Structure content into clear paragraphs
5. Fix grammar and punctuation while preserving key points
6. Remove filler words and redundancies
7. Keep important details and context
8. Format lists and bullet points properly
9. Add proper blog elements and sections
10. Give the output in Markdown format