I am recording audio from a microphone. My test records 10 seconds of PCM, converts it to a WAV and then sends the whole file to ACRcloud. However, I think it's possible to send smaller chunks of audio (say 1s x 10 chunks) that allows ACR cloud to start processing earlier, and possibly give a result after less that 10 seconds. Am I correct and if so, is it possible in python? Thanks
I am recording audio from a microphone. My test records 10 seconds of PCM, converts it to a WAV and then sends the whole file to ACRcloud. However, I think it's possible to send smaller chunks of audio (say 1s x 10 chunks) that allows ACR cloud to start processing earlier, and possibly give a result after less that 10 seconds. Am I correct and if so, is it possible in python? Thanks