Noise threshold detection
# support
e
hello, I'm wondering how to be able to do noise threshold detection, so that we can trigger a predefined action when the noise level exceeds a certain threshold. This is because when there is too much noise, we already know that the transcriber won't work and we want to activate a guided flow via the numeric keypad. Is this something feasible? Thank you! 🙂
v
@Enrico Citti Bertino Hello! Yes, noise threshold detection is definitely feasible and can be a smart way to manage environments where the noise level can interfere with voice recognition. To implement this, you would typically need to integrate a noise detection algorithm that monitors the ambient sound level in real-time. When the noise level exceeds the predefined threshold, the system can automatically switch to an alternative input method, such as a numeric keypad. The specifics of how to set this up would depend on the details of your current system and the technology stack you're using. You might need to use audio processing libraries or APIs that can analyze the sound and provide you with the necessary data to make decisions. If you need further assistance with the implementation or have any other questions, feel free to ask!
You can continue this conversation by mentioning me in the message.
Got it. Tagging @User for additional help.
e
Wondering if it's possible via a Vapi feature, cause I don't handle audio directly
s
@Enrico Citti Bertino to handle noise detection it has to be done via prompting.
what you can do is add in your prompt if user goes off the context or deviates from the then inform the user to get aside from noise place and focus on or
try incorporating this in your prompt accordingly.
e
Hi Shubham, thank you! But this is not exactly the case I meant because when there is a lot of noise unfortunately no input comes from the transcriber and the conversation remains "hanging". What can I do in this case?
s
if gibberish comes then it;s outisde the context ask the llm to instruct the user to set aside from noise bg
what else your thinking?
2 Views