I've been looking for a speech-to-text system that works well for a long time. I've tried various ones in the past, including the Daddy 'Dragon', which costs a fortune and is so incredibly clunky and slow (Even on a very fast PC), I just don't use it.

I work in AI and I pretty much live in front of my computer, so any time saving or labour saving that I can make is very valuable to me. What I really like about this is that it's quick and easy and works across all applications. Whether I'm typing into Visual Studio Code, Slack, or a Word document. In fact I'm writing this review using the system now.

The only thing I will say is that if you're serious about this, it's definitely going to be a good idea to get a higher tier. As I said, I've only been using it for a couple of hours and already I have burnt through nearly 3,000 of my 200,000 credits, so I will be upgrading to a higher tier.

When I first signed up I had a slight problem connecting to the system, but the great thing is support were on chat and answered my questions and got things sorted out in a matter of minutes. I think it was just a transient network error, so nothing under their control, but the key thing is they were there, which is very important.

I have absolutely no hesitation in recommending this, and as I say, I will be upgrading to tier 2 and probably tier 3. Don't let this one pass you by. It just makes working on the computer way easier.

Wishing you the very best of luck with the AppSumo launch.

A suggestion for the developers. Maybe you could add a bring your own API key so that I could wire it up to other LLMs if I needed to, maybe even LMStudio running locally or one of the models available on Open Router - That would be good for us, in that you would not need to limit the credits and it would significantly reduce your COGS. It might not run fast enough, though, using local models depending on the system.