hi
this is a great offline Open-Source-App for Speech-to-Text for all Desktop OS.
the big advantages are that its private, dont need cloud, is extensible, forks allowed and for win, mac and linux.
the GPU can be used for speeding up, if availiable.
there are different transcrib models sorted by accuracy and pause can be filtered out by VAD-Filter.
you can put the transcribtion in the now active input field.
Press a shortcut to start/stop recording (or use push-to-talk mode).
use one of Whisper or Parakeet models.
app details (short overview)
.opensource
.cross-platform
.privacy and offline
.customization and forks allowed
app site
https://handy.computer/
github project
https://github.com/cjpais/Handy
feel free to build a test build or add the app to App Directory.
thx
Please.
Follow the template ↓→ https://portableapps.com/forums/general/request_apps/request_guidelines
A link to its documentation is better than a personal explanation..
Emphasize the fact that's a Speech To Text and NOT Text To Speech app, to avoid any kind of misunderstanding.
PS. Looks very nice btw, but unable to run on my Windows 7 x64 machine.
'Life is a strategy game, where roles are already distributed'
― Neo Buddha ―