> usage > using veadotube > nodes > Audio

Audio nodes

utilities for nodes that output audio data.

Cherry Lip Sync audio.cherrylipsync

takes audio data and estimates lipsync animation information.

an optimised cross-platform alternative to Oculus Lip Sync.

MFCC audio.mfcc

turns audio data into coefficients that can be useful for phoneme/speaker recognition.

these coeficients can be pretty abstract; you can use its data by combining it with a Scores Match node, which then lets you record voice samples and thus calibrate your own lipsync solution, for example.

Oculus Lip Sync audio.ovrlipsync

takes audio data and estimates lipsync animation information.

this plugin was only released on desktop for x64 Windows and macOS. on Linux, veado runs the plugin through Wine if the user has installed. on Silicon macOS, veado runs it through Rosetta 2.

RNNoise audio.rnnoise

takes audio data and removes any potential noise, also estimates whether there’s speech present or not.

Silero VAD audio.silerovad

takes audio data and estimates whether there’s speech present or not.