Hello all! I’m trying to perform some speech-to-text transcription using google cloud speech. To do so I’m using the Audio Device In CHOP. In order to do so I need to know how the audio is encoded and haven’t been able to find out what it is (LINEAR16, FLAC, etc.).
Additionally I need to convert the audio sample data into binary. To do so do I need just the most recent channel value or the vals(), and what does the channel actually store? Is it the wave data, the amplitude, etc.?
Thank you for any help!