https://livekit.io logo
Join Slack
Powered by
i want to implement noice cancellation on my livek...
# ask-ai
d
i want to implement noice cancellation on my livekit self hosted, bvc or nc doesn't matter, how i can do that?
t
Thanks for reaching out, Ariel. I'm an AI assistant and I'm here to help. Give me a moment while I research this topic.
Just a quick heads-up: the enhanced noise cancellation with Krisp models, including Background Voice Cancellation (BVC), is available only on LiveKit Cloud and isn’t supported in self-hosted setups. If you’re running LiveKit on your own, no worries! You can still use WebRTC’s built-in noise suppression and echo cancellation, which are turned on by default. You can tweak these settings using the 
AudioCaptureOptions
type in the LiveKit SDKs when you connect. If top-notch noise cancellation is a must for you, you might want to check out LiveKit Cloud, where those advanced Krisp models are ready to go. Or, if you prefer sticking with self-hosted, you could try adding some client-side preprocessing to clean up the audio before it hits your server. Feel free to reach out if you want more info on any of these options or need a hand setting things up—I’m here to help! Sources: Sources/LiveKitKrispNoiseFilter/LiveKitKrispNoiseFilter.swift | Knowledge Management System | livekit/livekit_composite | DeepWiki | Enhanced noise cancellation | LiveKit Docs | Noise & echo cancellation | LiveKit Docs | Voice AI quickstart | LiveKit Docs
d
can i process it on the backend side?
t
Just a heads-up: enhanced noise cancellation with server-side processing isn’t available for self-hosted LiveKit setups. The advanced Krisp models that handle backend noise cancellation are only offered with LiveKit Cloud. But don’t worry! For self-hosted environments, you can still use WebRTC’s built-in audio processing features. These include basic noise suppression, echo cancellation, high-pass filtering, and auto gain control—all working during audio capture and transmission to help keep things clear. If you want to explore other ways to get similar results on your self-hosted setup, you might consider building custom audio processing pipelines on your backend or trying out third-party noise reduction libraries. Feel free to reach out if you’d like some tips or guidance on these options—I’m here to help! Sources: README.md | livekit-rtc/livekit/rtc/apm.py | Noise & echo cancellation | LiveKit Docs | Noise & echo cancellation | LiveKit Docs | Knowledge Management System | livekit/livekit_composite | DeepWiki
Open in Slack
PreviousNext
Powered by