Also, please hit me with any feedback, specifically for the documentation clarity and call quality.

My goal is to keep fundamental utilities and accessibility tools like translation services in the hands of small creators rather than some mega corporation, so I'm open to any improvement that can make that a reality.

Nic

Any chance you can include Burmese language?

I tried to, but the quality just isn't there. Eventually I'd like to, only if I can get the accuracy down.

The idea is great but you will never compete with a solution like Google translate: one simple reason is that Google Translate is highly specialized and optimized. Did you try to compare the processing time?

Running an opensource AI model to perform translation may help and work in some cases but to be honest this has also a lot of limitations. The first being processing time and the second languages support. I am not even considering accuracy.

Thanks for the feedback, you bring some good points to the table.

Did you try the demo on the landing page and notice considerable latency/accuracy slip ups?

Nice project!

A few questions/suggestions:

- It's not clear what the character limit would be if one was to sign-up. - What does "context-driven translations for higher accuracy" mean? - 35 characters are quite short for testing the translation of a complete sentence. Is there a reason for using such a short character length?

Hey, thanks for the feedback!

The character limit for an api call is 3000. I put it in the docs but could probably make it more obvious.

The context driven for higher accuracy is referencing what's going on under the hood, but on second thought it doesn't make much sense to put that there if I'm not going in depth about the under the hood stuff. I'll take that out.

35 character is quite short, you're right. I'll double it. The reason it was so short was arbitrary. I made it 100 now.

If you've got anything else send it over !

Nice. Do you have a secret sauce to get the price low or is it just a case of the usual overcharging by cloud providers?

Also read your twitter bio: I wont repeat here for privacy but would enjoy seeing stories about those things posted on HN

To the first question: A mix of both really. When you have a service this widespread, like translations, there's a lot in the vertical integration that can be more efficient. I mean, the project initiated from a different startup I built as a workaround for the cloud providers. It just evolved from that bottom-up thinking.

Thanks! Just for clarity, are you talking about the work experience, living situation, or startup ventures?

All of the above!

Okay! I'm still kinda new here, what exactly are you looking for? You could also reach out on twitter and we could talk more specifically

Tha translations worked great in my testing between Spanish/English.

How does it work? Is it essentially a fine-tuned LLM? If so, which base model?

I gave it a shot! Works really well.

Awesome!