How to make STT vosk from an audio window?

Question

I'm using Vosk in Python. How can I get sound from Windows in real-time? I'm looking forward to seeing how it goes around here.

I tried downloading test_speaker.py example from the alphacep/vosk-api repository on GitHub but it doesn't work anymore.

Answer 1

Does the code from this video fit your requirements? The video is in Russian, but I made a gist with its code.

You should download one of the language models, put it in the same directory with Python's script, and rename the directory containing the model to 'model'. You should also pip install two packages: vosk and pyaudio. Then you can run the script.