New Terpside version: faster, more accurate recognition, numbers in digits and a personal glossary. Download

About Terpside

Kevin · interpreter

I'm Kevin, a Spanish ↔ English medical interpreter from Latin America, with extensive experience interpreting for multiple companies. I work over the phone and by video for clinics and hospitals in the United States, through interpreting agencies. I interpret appointments, results, discharge instructions, pharmacy calls: conversations where a misheard number matters.

For a long time my second monitor was a stack of three tools that were not built for this: Windows captions, Chrome captions and a translator on top. They rewrote themselves while I read, showed only two or three sentences, and if I missed a number, it was gone.

In July 2026 I started building what I wanted to have: a single window that waits for the person to finish talking, shows the turn in its language with the translation underneath, and does not save the text, because nothing from a clinical call should stay on a disk. I have used it every shift since, and I keep refining it with what I know of the trade: medical terminology, the numbers that cannot be missed and the words that get confused over the phone.

That is Terpside: an interpreter's tool, shared with other interpreters. I sell it because colleagues asked me about it; the Free plan exists so anyone can try it on real calls without paying, and Pro is for whoever wants it all shift long.

Kevin, medical interpreter and creator of Terpside
July 2026
in daily use since
0
call data leaving your computer

How I build it

Terpside is written in Python and relies on open models that run on your computer: Moonshine (Moonshine AI, MIT license) to recognize, Whisper (OpenAI, MIT license) to tell the language and Opus-MT (University of Helsinki, CC BY 4.0) to translate. I chose Opus-MT over the alternative I tested (NLLB-200) because in my tests it translated the trade's vocabulary better, used one eighth of the CPU resources and its license allows selling it; full attributions are in the "About" screen.

I measure each change before keeping it: latency, CPU use, missing numbers and altered negations. When a test shows an idea does not work, it is dropped even if it sounded good.

Questions? Write to me

I reply myself. If you work differently than I do, I would like to hear about it.

Support and contact