Following this discussion and my comment :
It would be very very valuable if we could have access to the raw audio after a wake word.
For instance : "Hello bot, (... some audio ...)"
- Because it open the possibility to call LLM like ChatGPT and play back answer
- Because offline trigger to get the audio is very smart compared to always listening that send tons of request.
- Or at least a sample code to record audio just after a wakeword (assuming we do not loss some part) ?
Many thanks for your help. I can test the GPT parts but looking for a sample to get started retrieveing the audio from microphone.
Following this discussion and my comment :
It would be very very valuable if we could have access to the raw audio after a wake word.
For instance : "Hello bot, (... some audio ...)"
Many thanks for your help. I can test the GPT parts but looking for a sample to get started retrieveing the audio from microphone.