Hello everyone!
I managed to perform streaming speech recognition on a audio stream with the v1 version of the library thanks to the reported example in the tutorials.
I tried to the same with Speech V2 and since there is no example like in the first version, I took as reference the speech/snippets/transcribe_streaming_voice_activity_timeouts.py
Unfortunately it seems not working with the MicrophoneStream Class used in the v1 example.
Has anyone already implemented this feature? This question seems quite common (see here and here)
Thanks!
LinkedIn
Twitter
