[GCARC] N1MM Text To Speech feature

[Agustin Neron Properties LLC]

Hi all,
In recent weeks, N1MM programmers (K3CT and N1MM mainly) have created and implemented an amazing new feature in N1MM+ (pay attention you Field Day SSB operators!).
 
It is a text to speech feature. You type the call in the window, and pre-program macros for the exchange, calling CQ, QRZ, or anything you want to store, and a stored voice file is created from the stored exchange macro plus the callsign you just typed in your window.
 
The system is based on the Piper text to speech software engine (free version for ham radio use). In N1MM you can download samples of roughly 20 voice models (male and female). These are easy to set up, but these are  not your voice, you will sound on the air like the voice you selected.
 
Now here's the amazing part. K3CT made a full set of instructions to create your own "voice model". Once complete, the stored voice model will be your voice, sounding pretty much like you.
 
It's roughly a one hour process on Windows 11 (you have to run WSL which loads Linux/Ubuntu mode in Window 11, it does not work in Windows 10). When complete, you will then rename and load it into N1MM. With a little setup time, you will be hearing yourself calling CQ and working anyone you type in the Log window in no time!
 
I completed it and plan to use it in a couple weeks for ARRL Sweepstakes SSB. As you might know, SS has a lengthy exchange with serial numbers. This setup will take fatigue and sore throats out of the picture for a phone contest.
I would highly recommend this for the SSB Field Day ops next June.
You could be half asleep at 3AM on 75m and work stations hitting your F-keys!
 
Here's the page with the details at N1MM:
https://n1mmwp.hamdocs.com/setup/audio-setup-window/#text-to-speech-tab 
 
73 to all, and hope you enjoy checking this out,
 
Darrell AB2E