-
vosk-api
Offline speech recognition API for Android, iOS, Raspberry Pi and servers with Python, Java, C# and Node
-
InfluxDB
Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.
-
OpenBoard
OpenBoard is a cross-platform interactive whiteboard application intended for use in a classroom setting. (by OpenBoard-org)
Download And install; https://github.com/Felicis/vosk-android-demo Settings > System > Language & input > keyboards on-screen Keyboard > + manage On-screen Keyboards > Toggle on Vosk Demo > OK > OK enter a text field than select Vosk Demo Profit!
There are so many Systems & API's to use, these speech recognition models generally are around 50~200MB in size https://stackoverflow.com/questions/36277050/difference-between-online-and-offline-speech-to-text-conversion https://github.com/alphacep/vosk-api // API
https://github.com/ideasman42/nerd-dictation // linux
There are so many FOSS STT API's i think it's just a a matter interest & some one will nicely integrate in into a IME like OpenBoard & get an almost as good an Gboard experience.